mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-19 01:45:13 +00:00
Merge branch 'master' of https://github.com/rg3/youtube-dl
Conflicts: .gitignore LATEST_VERSION Makefile youtube-dl youtube-dl.exe youtube_dl/InfoExtractors.py youtube_dl/__init__.py
This commit is contained in:
Jeff Crouse
commit
258d5850c9
43 changed files with 6464 additions and 4994 deletions
24
.gitignore
vendored
24
.gitignore
vendored
|
|
@ -1,17 +1,19 @@
|
|||
*.pyc
|
||||
*.pyo
|
||||
*~
|
||||
*.DS_Store
|
||||
wine-py2exe/
|
||||
py2exe.log
|
||||
youtube-dl
|
||||
*.kate-swp
|
||||
build/
|
||||
dist/
|
||||
MANIFEST
|
||||
README.txt
|
||||
youtube-dl.1
|
||||
LATEST_VERSION
|
||||
|
||||
#OS X
|
||||
.DS_Store
|
||||
.AppleDouble
|
||||
.LSOverride
|
||||
Icon
|
||||
._*
|
||||
.Spotlight-V100
|
||||
.Trashes
|
||||
youtube-dl.bash-completion
|
||||
youtube-dl
|
||||
youtube-dl.exe
|
||||
youtube-dl.tar.gz
|
||||
.coverage
|
||||
cover/
|
||||
updates_key.pem
|
||||
|
|
|
|||
17
.tarignore
Normal file
17
.tarignore
Normal file
|
|
@ -0,0 +1,17 @@
|
|||
updates_key.pem
|
||||
*.pyc
|
||||
*.pyo
|
||||
youtube-dl.exe
|
||||
wine-py2exe/
|
||||
py2exe.log
|
||||
*.kate-swp
|
||||
build/
|
||||
dist/
|
||||
MANIFEST
|
||||
*.DS_Store
|
||||
youtube-dl.tar.gz
|
||||
.coverage
|
||||
cover/
|
||||
__pycache__/
|
||||
.git/
|
||||
*~
|
||||
15
.travis.yml
15
.travis.yml
|
|
@ -1,9 +1,14 @@
|
|||
language: python
|
||||
#specify the python version
|
||||
python:
|
||||
- "2.6"
|
||||
- "2.7"
|
||||
#command to install the setup
|
||||
install:
|
||||
# command to run tests
|
||||
script: nosetests test --nocapture
|
||||
- "3.3"
|
||||
script: nosetests test --verbose
|
||||
notifications:
|
||||
email:
|
||||
- filippo.valsorda@gmail.com
|
||||
- phihag@phihag.de
|
||||
irc:
|
||||
channels:
|
||||
- "irc.freenode.org#youtube-dl"
|
||||
skip_join: true
|
||||
|
|
|
|||
14
CHANGELOG
Normal file
14
CHANGELOG
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
2013.01.02 Codename: GIULIA
|
||||
|
||||
* Add support for ComedyCentral clips <nto>
|
||||
* Corrected Vimeo description fetching <Nick Daniels>
|
||||
* Added the --no-post-overwrites argument <Barbu Paul - Gheorghe>
|
||||
* --verbose offers more environment info
|
||||
* New info_dict field: uploader_id
|
||||
* New updates system, with signature checking
|
||||
* New IEs: NBA, JustinTV, FunnyOrDie, TweetReel, Steam, Ustream
|
||||
* Fixed IEs: BlipTv
|
||||
* Fixed for Python 3 IEs: Xvideo, Youku, XNXX, Dailymotion, Vimeo, InfoQ
|
||||
* Simplified IEs and test code
|
||||
* Various (Python 3 and other) fixes
|
||||
* Revamped and expanded tests
|
||||
1
LATEST_VERSION
Normal file
1
LATEST_VERSION
Normal file
|
|
@ -0,0 +1 @@
|
|||
2012.10.09
|
||||
24
LICENSE
Normal file
24
LICENSE
Normal file
|
|
@ -0,0 +1,24 @@
|
|||
This is free and unencumbered software released into the public domain.
|
||||
|
||||
Anyone is free to copy, modify, publish, use, compile, sell, or
|
||||
distribute this software, either in source code form or as a compiled
|
||||
binary, for any purpose, commercial or non-commercial, and by any
|
||||
means.
|
||||
|
||||
In jurisdictions that recognize copyright laws, the author or authors
|
||||
of this software dedicate any and all copyright interest in the
|
||||
software to the public domain. We make this dedication for the benefit
|
||||
of the public at large and to the detriment of our heirs and
|
||||
successors. We intend this dedication to be an overt act of
|
||||
relinquishment in perpetuity of all present and future rights to this
|
||||
software under copyright law.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
||||
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
|
||||
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
|
||||
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
|
||||
OTHER DEALINGS IN THE SOFTWARE.
|
||||
|
||||
For more information, please refer to <http://unlicense.org/>
|
||||
3
MANIFEST.in
Normal file
3
MANIFEST.in
Normal file
|
|
@ -0,0 +1,3 @@
|
|||
include README.md
|
||||
include test/*.py
|
||||
include test/*.json
|
||||
50
Makefile
50
Makefile
|
|
@ -1,8 +1,7 @@
|
|||
all: youtube-dl README.md youtube-dl.1 youtube-dl.bash-completion LATEST_VERSION
|
||||
# TODO: re-add youtube-dl.exe, and make sure it's 1. safe and 2. doesn't need sudo
|
||||
all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
|
||||
|
||||
clean:
|
||||
rm -f youtube-dl youtube-dl.exe youtube-dl.1 LATEST_VERSION youtube_dl/*.pyc
|
||||
rm -rf youtube-dl youtube-dl.exe youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/
|
||||
|
||||
PREFIX=/usr/local
|
||||
BINDIR=$(PREFIX)/bin
|
||||
|
|
@ -17,43 +16,32 @@ install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
|
|||
install -d $(DESTDIR)$(SYSCONFDIR)/bash_completion.d
|
||||
install -m 644 youtube-dl.bash-completion $(DESTDIR)$(SYSCONFDIR)/bash_completion.d/youtube-dl
|
||||
|
||||
.PHONY: all clean install youtube-dl.bash-completion
|
||||
# TODO un-phony README.md and youtube-dl.bash_completion by reading from .in files and generating from them
|
||||
test:
|
||||
#nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose --processes 4 test
|
||||
nosetests --verbose test
|
||||
|
||||
.PHONY: all clean install test
|
||||
|
||||
youtube-dl: youtube_dl/*.py
|
||||
zip --quiet --junk-paths youtube-dl youtube_dl/*.py
|
||||
zip --quiet youtube-dl youtube_dl/*.py
|
||||
zip --quiet --junk-paths youtube-dl youtube_dl/__main__.py
|
||||
echo '#!/usr/bin/env python' > youtube-dl
|
||||
cat youtube-dl.zip >> youtube-dl
|
||||
rm youtube-dl.zip
|
||||
chmod a+x youtube-dl
|
||||
|
||||
youtube-dl.exe: youtube_dl/*.py
|
||||
bash devscripts/wine-py2exe.sh build_exe.py
|
||||
|
||||
README.md: youtube_dl/*.py
|
||||
@options=$$(COLUMNS=80 python -m youtube_dl --help | sed -e '1,/.*General Options.*/ d' -e 's/^\W\{2\}\(\w\)/## \1/') && \
|
||||
header=$$(sed -e '/.*# OPTIONS/,$$ d' README.md) && \
|
||||
footer=$$(sed -e '1,/.*# FAQ/ d' README.md) && \
|
||||
echo "$${header}" > README.md && \
|
||||
echo >> README.md && \
|
||||
echo '# OPTIONS' >> README.md && \
|
||||
echo "$${options}" >> README.md&& \
|
||||
echo >> README.md && \
|
||||
echo '# FAQ' >> README.md && \
|
||||
echo "$${footer}" >> README.md
|
||||
COLUMNS=80 python -m youtube_dl --help | python devscripts/make_readme.py
|
||||
|
||||
youtube-dl.1:
|
||||
pandoc -s -w man README.md -o youtube-dl.1
|
||||
README.txt: README.md
|
||||
pandoc -f markdown -t plain README.md -o README.txt
|
||||
|
||||
youtube-dl.bash-completion:
|
||||
@options=`egrep -o '(--[a-z-]+) ' README.md | sort -u | xargs echo` && \
|
||||
content=`sed "s/opts=\"[^\"]*\"/opts=\"$${options}\"/g" youtube-dl.bash-completion` && \
|
||||
echo "$${content}" > youtube-dl.bash-completion
|
||||
youtube-dl.1: README.md
|
||||
pandoc -s -f markdown -t man README.md -o youtube-dl.1
|
||||
|
||||
LATEST_VERSION: youtube_dl/__init__.py
|
||||
python -m youtube_dl --version > LATEST_VERSION
|
||||
youtube-dl.bash-completion: youtube_dl/*.py devscripts/bash-completion.in
|
||||
python devscripts/bash-completion.py
|
||||
|
||||
test:
|
||||
nosetests2 --nocapture test
|
||||
|
||||
.PHONY: default compile update update-latest update-readme test clean
|
||||
youtube-dl.tar.gz: all
|
||||
tar -cvzf youtube-dl.tar.gz -s "|^./|./youtube-dl/|" \
|
||||
--exclude-from=".tarignore" -- .
|
||||
|
|
|
|||
70
README.md
70
README.md
|
|
@ -1,4 +1,4 @@
|
|||
% youtube-dl(1)
|
||||
% YOUTUBE-DL(1)
|
||||
|
||||
# NAME
|
||||
youtube-dl
|
||||
|
|
@ -20,6 +20,11 @@ # OPTIONS
|
|||
-i, --ignore-errors continue on download errors
|
||||
-r, --rate-limit LIMIT download rate limit (e.g. 50k or 44.6m)
|
||||
-R, --retries RETRIES number of retries (default is 10)
|
||||
--buffer-size SIZE size of download buffer (e.g. 1024 or 16k) (default
|
||||
is 1024)
|
||||
--no-resize-buffer do not automatically adjust the buffer size. By
|
||||
default, the buffer size is automatically resized
|
||||
from an initial value of SIZE.
|
||||
--dump-user-agent display the current browser identification
|
||||
--user-agent UA specify a custom user agent
|
||||
--list-extractors List all supported extractors and the URLs they
|
||||
|
|
@ -37,16 +42,22 @@ # OPTIONS
|
|||
Filesystem Options:
|
||||
-t, --title use title in file name
|
||||
--id use video ID in file name
|
||||
-l, --literal use literal title in file name
|
||||
-l, --literal [deprecated] alias of --title
|
||||
-A, --auto-number number downloaded files starting from 00000
|
||||
-o, --output TEMPLATE output filename template. Use %(stitle)s to get the
|
||||
-o, --output TEMPLATE output filename template. Use %(title)s to get the
|
||||
title, %(uploader)s for the uploader name,
|
||||
%(autonumber)s to get an automatically incremented
|
||||
number, %(ext)s for the filename extension,
|
||||
%(upload_date)s for the upload date (YYYYMMDD),
|
||||
%(extractor)s for the provider (youtube, metacafe,
|
||||
etc), %(id)s for the video id and %% for a literal
|
||||
percent. Use - to output to stdout.
|
||||
%(uploader_id)s for the uploader nickname if
|
||||
different, %(autonumber)s to get an automatically
|
||||
incremented number, %(ext)s for the filename
|
||||
extension, %(upload_date)s for the upload date
|
||||
(YYYYMMDD), %(extractor)s for the provider
|
||||
(youtube, metacafe, etc), %(id)s for the video id
|
||||
and %% for a literal percent. Use - to output to
|
||||
stdout. Can also be used to download to a different
|
||||
directory, for example with -o '/my/downloads/%(upl
|
||||
oader)s/%(title)s-%(id)s.%(ext)s' .
|
||||
--restrict-filenames Restrict filenames to only ASCII characters, and
|
||||
avoid "&" and spaces in filenames
|
||||
-a, --batch-file FILE file containing URLs to download ('-' for stdin)
|
||||
-w, --no-overwrites do not overwrite files
|
||||
-c, --continue resume partially downloaded files
|
||||
|
|
@ -101,6 +112,34 @@ # OPTIONS
|
|||
specific bitrate like 128K (default 5)
|
||||
-k, --keep-video keeps the video file on disk after the post-
|
||||
processing; the video is erased by default
|
||||
--no-post-overwrites do not overwrite post-processed files; the post-
|
||||
processed files are overwritten by default
|
||||
|
||||
# CONFIGURATION
|
||||
|
||||
You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.local/config/youtube-dl.conf`.
|
||||
|
||||
# OUTPUT TEMPLATE
|
||||
|
||||
The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parenthesis, followed by a lowercase S. Allowed names are:
|
||||
|
||||
- `id`: The sequence will be replaced by the video identifier.
|
||||
- `url`: The sequence will be replaced by the video URL.
|
||||
- `uploader`: The sequence will be replaced by the nickname of the person who uploaded the video.
|
||||
- `upload_date`: The sequence will be replaced by the upload date in YYYYMMDD format.
|
||||
- `title`: The sequence will be replaced by the video title.
|
||||
- `ext`: The sequence will be replaced by the appropriate extension (like flv or mp4).
|
||||
- `epoch`: The sequence will be replaced by the Unix epoch when creating the file.
|
||||
- `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero.
|
||||
|
||||
The current default template is `%(id)s.%(ext)s`, but that will be switchted to `%(title)s-%(id)s.%(ext)s` (which can be requested with `-t` at the moment).
|
||||
|
||||
In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title:
|
||||
|
||||
$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc
|
||||
youtube-dl test video ''_ä↭𝕐.mp4 # All kinds of weird characters
|
||||
$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames
|
||||
youtube-dl_test_video_.mp4 # A simple file name
|
||||
|
||||
# FAQ
|
||||
|
||||
|
|
@ -137,17 +176,9 @@ ### SyntaxError: Non-ASCII character ###
|
|||
|
||||
means you're using an outdated version of Python. Please update to Python 2.6 or 2.7.
|
||||
|
||||
To run youtube-dl under Python 2.5, you'll have to manually check it out like this:
|
||||
|
||||
git clone git://github.com/rg3/youtube-dl.git
|
||||
cd youtube-dl
|
||||
python -m youtube_dl --help
|
||||
|
||||
Please note that Python 2.5 is not supported anymore.
|
||||
|
||||
### What is this binary file? Where has the code gone?
|
||||
|
||||
Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repo to see the code. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make compile`.
|
||||
Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`.
|
||||
|
||||
### The exe throws a *Runtime error from Visual C++*
|
||||
|
||||
|
|
@ -166,6 +197,9 @@ # BUGS
|
|||
Please include:
|
||||
|
||||
* Your exact command line, like `youtube-dl -t "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title"`. A common mistake is not to escape the `&`. Putting URLs in quotes should solve this problem.
|
||||
* If possible re-run the command with `--verbose`, and include the full output, it is really helpful to us.
|
||||
* The output of `youtube-dl --version`
|
||||
* The output of `python --version`
|
||||
* The name and version of your Operating System ("Ubuntu 11.04 x64" or "Windows 7 x64" is usually enough).
|
||||
|
||||
For discussions, join us in the irc channel #youtube-dl on freenode.
|
||||
|
|
|
|||
6
bin/youtube-dl
Executable file
6
bin/youtube-dl
Executable file
|
|
@ -0,0 +1,6 @@
|
|||
#!/usr/bin/env python
|
||||
|
||||
import youtube_dl
|
||||
|
||||
if __name__ == '__main__':
|
||||
youtube_dl.main()
|
||||
48
build_exe.py
48
build_exe.py
|
|
@ -1,48 +0,0 @@
|
|||
from distutils.core import setup
|
||||
import py2exe
|
||||
import sys, os
|
||||
|
||||
"""This will create an exe that needs Microsoft Visual C++ 2008 Redistributable Package"""
|
||||
|
||||
# If run without args, build executables
|
||||
if len(sys.argv) == 1:
|
||||
sys.argv.append("py2exe")
|
||||
|
||||
# os.chdir(os.path.dirname(os.path.abspath(sys.argv[0]))) # conflict with wine-py2exe.sh
|
||||
sys.path.append('./youtube_dl')
|
||||
|
||||
options = {
|
||||
"bundle_files": 1,
|
||||
"compressed": 1,
|
||||
"optimize": 2,
|
||||
"dist_dir": '.',
|
||||
"dll_excludes": ['w9xpopen.exe']
|
||||
}
|
||||
|
||||
console = [{
|
||||
"script":"./youtube_dl/__main__.py",
|
||||
"dest_base": "youtube-dl",
|
||||
}]
|
||||
|
||||
init_file = open('./youtube_dl/__init__.py')
|
||||
for line in init_file.readlines():
|
||||
if line.startswith('__version__'):
|
||||
version = line[11:].strip(" ='\n")
|
||||
break
|
||||
else:
|
||||
version = ''
|
||||
|
||||
setup(name='youtube-dl',
|
||||
version=version,
|
||||
description='Small command-line program to download videos from YouTube.com and other video sites',
|
||||
url='https://github.com/rg3/youtube-dl',
|
||||
packages=['youtube_dl'],
|
||||
|
||||
console = console,
|
||||
options = {"py2exe": options},
|
||||
zipfile = None,
|
||||
)
|
||||
|
||||
import shutil
|
||||
shutil.rmtree("build")
|
||||
|
||||
14
devscripts/bash-completion.in
Normal file
14
devscripts/bash-completion.in
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
__youtube-dl()
|
||||
{
|
||||
local cur prev opts
|
||||
COMPREPLY=()
|
||||
cur="${COMP_WORDS[COMP_CWORD]}"
|
||||
opts="{{flags}}"
|
||||
|
||||
if [[ ${cur} == * ]] ; then
|
||||
COMPREPLY=( $(compgen -W "${opts}" -- ${cur}) )
|
||||
return 0
|
||||
fi
|
||||
}
|
||||
|
||||
complete -F __youtube-dl youtube-dl
|
||||
26
devscripts/bash-completion.py
Executable file
26
devscripts/bash-completion.py
Executable file
|
|
@ -0,0 +1,26 @@
|
|||
#!/usr/bin/env python
|
||||
import os
|
||||
from os.path import dirname as dirn
|
||||
import sys
|
||||
|
||||
sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
|
||||
import youtube_dl
|
||||
|
||||
BASH_COMPLETION_FILE = "youtube-dl.bash-completion"
|
||||
BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in"
|
||||
|
||||
def build_completion(opt_parser):
|
||||
opts_flag = []
|
||||
for group in opt_parser.option_groups:
|
||||
for option in group.option_list:
|
||||
#for every long flag
|
||||
opts_flag.append(option.get_opt_string())
|
||||
with open(BASH_COMPLETION_TEMPLATE) as f:
|
||||
template = f.read()
|
||||
with open(BASH_COMPLETION_FILE, "w") as f:
|
||||
#just using the special char
|
||||
filled_template = template.replace("{{flags}}", " ".join(opts_flag))
|
||||
f.write(filled_template)
|
||||
|
||||
parser = youtube_dl.parseOpts()[0]
|
||||
build_completion(parser)
|
||||
33
devscripts/gh-pages/add-version.py
Executable file
33
devscripts/gh-pages/add-version.py
Executable file
|
|
@ -0,0 +1,33 @@
|
|||
#!/usr/bin/env python3
|
||||
|
||||
import json
|
||||
import sys
|
||||
import hashlib
|
||||
import urllib.request
|
||||
|
||||
if len(sys.argv) <= 1:
|
||||
print('Specify the version number as parameter')
|
||||
sys.exit()
|
||||
version = sys.argv[1]
|
||||
|
||||
with open('update/LATEST_VERSION', 'w') as f:
|
||||
f.write(version)
|
||||
|
||||
versions_info = json.load(open('update/versions.json'))
|
||||
if 'signature' in versions_info:
|
||||
del versions_info['signature']
|
||||
|
||||
new_version = {}
|
||||
|
||||
filenames = {'bin': 'youtube-dl', 'exe': 'youtube-dl.exe', 'tar': 'youtube-dl-%s.tar.gz' % version}
|
||||
for key, filename in filenames.items():
|
||||
print('Downloading and checksumming %s...' %filename)
|
||||
url = 'http://youtube-dl.org/downloads/%s/%s' % (version, filename)
|
||||
data = urllib.request.urlopen(url).read()
|
||||
sha256sum = hashlib.sha256(data).hexdigest()
|
||||
new_version[key] = (url, sha256sum)
|
||||
|
||||
versions_info['versions'][version] = new_version
|
||||
versions_info['latest'] = version
|
||||
|
||||
json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True)
|
||||
32
devscripts/gh-pages/generate-download.py
Executable file
32
devscripts/gh-pages/generate-download.py
Executable file
|
|
@ -0,0 +1,32 @@
|
|||
#!/usr/bin/env python3
|
||||
import hashlib
|
||||
import shutil
|
||||
import subprocess
|
||||
import tempfile
|
||||
import urllib.request
|
||||
import json
|
||||
|
||||
versions_info = json.load(open('update/versions.json'))
|
||||
version = versions_info['latest']
|
||||
URL = versions_info['versions'][version]['bin'][0]
|
||||
|
||||
data = urllib.request.urlopen(URL).read()
|
||||
|
||||
# Read template page
|
||||
with open('download.html.in', 'r', encoding='utf-8') as tmplf:
|
||||
template = tmplf.read()
|
||||
|
||||
md5sum = hashlib.md5(data).hexdigest()
|
||||
sha1sum = hashlib.sha1(data).hexdigest()
|
||||
sha256sum = hashlib.sha256(data).hexdigest()
|
||||
template = template.replace('@PROGRAM_VERSION@', version)
|
||||
template = template.replace('@PROGRAM_URL@', URL)
|
||||
template = template.replace('@PROGRAM_MD5SUM@', md5sum)
|
||||
template = template.replace('@PROGRAM_SHA1SUM@', sha1sum)
|
||||
template = template.replace('@PROGRAM_SHA256SUM@', sha256sum)
|
||||
template = template.replace('@EXE_URL@', versions_info['versions'][version]['exe'][0])
|
||||
template = template.replace('@EXE_SHA256SUM@', versions_info['versions'][version]['exe'][1])
|
||||
template = template.replace('@TAR_URL@', versions_info['versions'][version]['tar'][0])
|
||||
template = template.replace('@TAR_SHA256SUM@', versions_info['versions'][version]['tar'][1])
|
||||
with open('download.html', 'w', encoding='utf-8') as dlf:
|
||||
dlf.write(template)
|
||||
28
devscripts/gh-pages/sign-versions.py
Executable file
28
devscripts/gh-pages/sign-versions.py
Executable file
|
|
@ -0,0 +1,28 @@
|
|||
#!/usr/bin/env python3
|
||||
|
||||
import rsa
|
||||
import json
|
||||
from binascii import hexlify
|
||||
|
||||
versions_info = json.load(open('update/versions.json'))
|
||||
if 'signature' in versions_info:
|
||||
del versions_info['signature']
|
||||
|
||||
print('Enter the PKCS1 private key, followed by a blank line:')
|
||||
privkey = ''
|
||||
while True:
|
||||
try:
|
||||
line = input()
|
||||
except EOFError:
|
||||
break
|
||||
if line == '':
|
||||
break
|
||||
privkey += line + '\n'
|
||||
privkey = bytes(privkey, 'ascii')
|
||||
privkey = rsa.PrivateKey.load_pkcs1(privkey)
|
||||
|
||||
signature = hexlify(rsa.pkcs1.sign(json.dumps(versions_info, sort_keys=True).encode('utf-8'), privkey, 'SHA-256')).decode()
|
||||
print('signature: ' + signature)
|
||||
|
||||
versions_info['signature'] = signature
|
||||
json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True)
|
||||
21
devscripts/gh-pages/update-copyright.py
Executable file
21
devscripts/gh-pages/update-copyright.py
Executable file
|
|
@ -0,0 +1,21 @@
|
|||
#!/usr/bin/env python
|
||||
# coding: utf-8
|
||||
|
||||
from __future__ import with_statement
|
||||
|
||||
import datetime
|
||||
import glob
|
||||
import io # For Python 2 compatibilty
|
||||
import os
|
||||
import re
|
||||
|
||||
year = str(datetime.datetime.now().year)
|
||||
for fn in glob.glob('*.html*'):
|
||||
with io.open(fn, encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
newc = re.sub(u'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', u'Copyright © 2006-' + year, content)
|
||||
if content != newc:
|
||||
tmpFn = fn + '.part'
|
||||
with io.open(tmpFn, 'wt', encoding='utf-8') as outf:
|
||||
outf.write(newc)
|
||||
os.rename(tmpFn, fn)
|
||||
20
devscripts/make_readme.py
Executable file
20
devscripts/make_readme.py
Executable file
|
|
@ -0,0 +1,20 @@
|
|||
import sys
|
||||
import re
|
||||
|
||||
README_FILE = 'README.md'
|
||||
helptext = sys.stdin.read()
|
||||
|
||||
with open(README_FILE) as f:
|
||||
oldreadme = f.read()
|
||||
|
||||
header = oldreadme[:oldreadme.index('# OPTIONS')]
|
||||
footer = oldreadme[oldreadme.index('# CONFIGURATION'):]
|
||||
|
||||
options = helptext[helptext.index(' General Options:')+19:]
|
||||
options = re.sub(r'^ (\w.+)$', r'## \1', options, flags=re.M)
|
||||
options = '# OPTIONS\n' + options + '\n'
|
||||
|
||||
with open(README_FILE, 'w') as f:
|
||||
f.write(header)
|
||||
f.write(options)
|
||||
f.write(footer)
|
||||
|
|
@ -1,11 +1,85 @@
|
|||
#!/bin/sh
|
||||
|
||||
# IMPORTANT: the following assumptions are made
|
||||
# * the GH repo is on the origin remote
|
||||
# * the gh-pages branch is named so locally
|
||||
# * the git config user.signingkey is properly set
|
||||
|
||||
# You will need
|
||||
# pip install coverage nose rsa
|
||||
|
||||
# TODO
|
||||
# release notes
|
||||
# make hash on local files
|
||||
|
||||
set -e
|
||||
|
||||
if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi
|
||||
version="$1"
|
||||
if [ ! -z "`git tag | grep "$version"`" ]; then echo 'ERROR: version already present'; exit 1; fi
|
||||
if [ ! -z "`git status --porcelain`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi
|
||||
sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/__init__.py
|
||||
make all
|
||||
git add -A
|
||||
if [ ! -z "`git status --porcelain | grep -v CHANGELOG`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi
|
||||
if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
|
||||
|
||||
echo "\n### First of all, testing..."
|
||||
make clean
|
||||
nosetests --with-coverage --cover-package=youtube_dl --cover-html test || exit 1
|
||||
|
||||
echo "\n### Changing version in version.py..."
|
||||
sed -i~ "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
|
||||
|
||||
echo "\n### Committing CHANGELOG README.md and youtube_dl/version.py..."
|
||||
make README.md
|
||||
git add CHANGELOG README.md youtube_dl/version.py
|
||||
git commit -m "release $version"
|
||||
git tag -m "Release $version" "$version"
|
||||
|
||||
echo "\n### Now tagging, signing and pushing..."
|
||||
git tag -s -m "Release $version" "$version"
|
||||
git show "$version"
|
||||
read -p "Is it good, can I push? (y/n) " -n 1
|
||||
if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
|
||||
echo
|
||||
MASTER=$(git rev-parse --abbrev-ref HEAD)
|
||||
git push origin $MASTER:master
|
||||
git push origin "$version"
|
||||
|
||||
echo "\n### OK, now it is time to build the binaries..."
|
||||
REV=$(git rev-parse HEAD)
|
||||
make youtube-dl youtube-dl.tar.gz
|
||||
wget "http://jeromelaheurte.net:8142/download/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe || \
|
||||
wget "http://jeromelaheurte.net:8142/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
|
||||
mkdir -p "update_staging/$version"
|
||||
mv youtube-dl youtube-dl.exe "update_staging/$version"
|
||||
mv youtube-dl.tar.gz "update_staging/$version/youtube-dl-$version.tar.gz"
|
||||
RELEASE_FILES=youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz
|
||||
(cd update_staging/$version/ && md5sum $RELEASE_FILES > MD5SUMS)
|
||||
(cd update_staging/$version/ && sha1sum $RELEASE_FILES > SHA1SUMS)
|
||||
(cd update_staging/$version/ && sha256sum $RELEASE_FILES > SHA2-256SUMS)
|
||||
(cd update_staging/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
|
||||
git checkout HEAD -- youtube-dl youtube-dl.exe
|
||||
|
||||
echo "\n### Signing and uploading the new binaries to youtube-dl.org..."
|
||||
for f in $RELEASE_FILES; do gpg --detach-sig "update_staging/$version/$f"; done
|
||||
scp -r "update_staging/$version" ytdl@youtube-dl.org:html/downloads/
|
||||
rm -r update_staging
|
||||
|
||||
echo "\n### Now switching to gh-pages..."
|
||||
git checkout gh-pages
|
||||
git checkout "$MASTER" -- devscripts/gh-pages/
|
||||
git reset devscripts/gh-pages/
|
||||
devscripts/gh-pages/add-version.py $version
|
||||
devscripts/gh-pages/sign-versions.py < updates_key.pem
|
||||
devscripts/gh-pages/generate-download.py
|
||||
devscripts/gh-pages/update-copyright.py
|
||||
rm -r test_coverage
|
||||
mv cover test_coverage
|
||||
git add *.html *.html.in update test_coverage
|
||||
git commit -m "release $version"
|
||||
git show HEAD
|
||||
read -p "Is it good, can I push? (y/n) " -n 1
|
||||
if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
|
||||
echo
|
||||
git push origin gh-pages
|
||||
|
||||
echo "\n### DONE!"
|
||||
rm -r devscripts
|
||||
git checkout $MASTER
|
||||
|
|
|
|||
40
devscripts/transition_helper.py
Normal file
40
devscripts/transition_helper.py
Normal file
|
|
@ -0,0 +1,40 @@
|
|||
#!/usr/bin/env python
|
||||
|
||||
import sys, os
|
||||
|
||||
try:
|
||||
import urllib.request as compat_urllib_request
|
||||
except ImportError: # Python 2
|
||||
import urllib2 as compat_urllib_request
|
||||
|
||||
sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
|
||||
sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
|
||||
sys.stderr.write(u'The new location of the binaries is https://github.com/rg3/youtube-dl/downloads, not the git repository.\n\n')
|
||||
|
||||
try:
|
||||
raw_input()
|
||||
except NameError: # Python 3
|
||||
input()
|
||||
|
||||
filename = sys.argv[0]
|
||||
|
||||
API_URL = "https://api.github.com/repos/rg3/youtube-dl/downloads"
|
||||
BIN_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl"
|
||||
|
||||
if not os.access(filename, os.W_OK):
|
||||
sys.exit('ERROR: no write permissions on %s' % filename)
|
||||
|
||||
try:
|
||||
urlh = compat_urllib_request.urlopen(BIN_URL)
|
||||
newcontent = urlh.read()
|
||||
urlh.close()
|
||||
except (IOError, OSError) as err:
|
||||
sys.exit('ERROR: unable to download latest version')
|
||||
|
||||
try:
|
||||
with open(filename, 'wb') as outf:
|
||||
outf.write(newcontent)
|
||||
except (IOError, OSError) as err:
|
||||
sys.exit('ERROR: unable to overwrite current version')
|
||||
|
||||
sys.stderr.write(u'Done! Now you can run youtube-dl.\n')
|
||||
12
devscripts/transition_helper_exe/setup.py
Normal file
12
devscripts/transition_helper_exe/setup.py
Normal file
|
|
@ -0,0 +1,12 @@
|
|||
from distutils.core import setup
|
||||
import py2exe
|
||||
|
||||
py2exe_options = {
|
||||
"bundle_files": 1,
|
||||
"compressed": 1,
|
||||
"optimize": 2,
|
||||
"dist_dir": '.',
|
||||
"dll_excludes": ['w9xpopen.exe']
|
||||
}
|
||||
|
||||
setup(console=['youtube-dl.py'], options={ "py2exe": py2exe_options }, zipfile=None)
|
||||
102
devscripts/transition_helper_exe/youtube-dl.py
Normal file
102
devscripts/transition_helper_exe/youtube-dl.py
Normal file
|
|
@ -0,0 +1,102 @@
|
|||
#!/usr/bin/env python
|
||||
|
||||
import sys, os
|
||||
import urllib2
|
||||
import json, hashlib
|
||||
|
||||
def rsa_verify(message, signature, key):
|
||||
from struct import pack
|
||||
from hashlib import sha256
|
||||
from sys import version_info
|
||||
def b(x):
|
||||
if version_info[0] == 2: return x
|
||||
else: return x.encode('latin1')
|
||||
assert(type(message) == type(b('')))
|
||||
block_size = 0
|
||||
n = key[0]
|
||||
while n:
|
||||
block_size += 1
|
||||
n >>= 8
|
||||
signature = pow(int(signature, 16), key[1], key[0])
|
||||
raw_bytes = []
|
||||
while signature:
|
||||
raw_bytes.insert(0, pack("B", signature & 0xFF))
|
||||
signature >>= 8
|
||||
signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
|
||||
if signature[0:2] != b('\x00\x01'): return False
|
||||
signature = signature[2:]
|
||||
if not b('\x00') in signature: return False
|
||||
signature = signature[signature.index(b('\x00'))+1:]
|
||||
if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
|
||||
signature = signature[19:]
|
||||
if signature != sha256(message).digest(): return False
|
||||
return True
|
||||
|
||||
sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
|
||||
sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
|
||||
sys.stderr.write(u'From now on, get the binaries from http://rg3.github.com/youtube-dl/download.html, not from the git repository.\n\n')
|
||||
|
||||
raw_input()
|
||||
|
||||
filename = sys.argv[0]
|
||||
|
||||
UPDATE_URL = "http://rg3.github.com/youtube-dl/update/"
|
||||
VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
|
||||
JSON_URL = UPDATE_URL + 'versions.json'
|
||||
UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
|
||||
|
||||
if not os.access(filename, os.W_OK):
|
||||
sys.exit('ERROR: no write permissions on %s' % filename)
|
||||
|
||||
exe = os.path.abspath(filename)
|
||||
directory = os.path.dirname(exe)
|
||||
if not os.access(directory, os.W_OK):
|
||||
sys.exit('ERROR: no write permissions on %s' % directory)
|
||||
|
||||
try:
|
||||
versions_info = urllib2.urlopen(JSON_URL).read().decode('utf-8')
|
||||
versions_info = json.loads(versions_info)
|
||||
except:
|
||||
sys.exit(u'ERROR: can\'t obtain versions info. Please try again later.')
|
||||
if not 'signature' in versions_info:
|
||||
sys.exit(u'ERROR: the versions file is not signed or corrupted. Aborting.')
|
||||
signature = versions_info['signature']
|
||||
del versions_info['signature']
|
||||
if not rsa_verify(json.dumps(versions_info, sort_keys=True), signature, UPDATES_RSA_KEY):
|
||||
sys.exit(u'ERROR: the versions file signature is invalid. Aborting.')
|
||||
|
||||
version = versions_info['versions'][versions_info['latest']]
|
||||
|
||||
try:
|
||||
urlh = urllib2.urlopen(version['exe'][0])
|
||||
newcontent = urlh.read()
|
||||
urlh.close()
|
||||
except (IOError, OSError) as err:
|
||||
sys.exit('ERROR: unable to download latest version')
|
||||
|
||||
newcontent_hash = hashlib.sha256(newcontent).hexdigest()
|
||||
if newcontent_hash != version['exe'][1]:
|
||||
sys.exit(u'ERROR: the downloaded file hash does not match. Aborting.')
|
||||
|
||||
try:
|
||||
with open(exe + '.new', 'wb') as outf:
|
||||
outf.write(newcontent)
|
||||
except (IOError, OSError) as err:
|
||||
sys.exit(u'ERROR: unable to write the new version')
|
||||
|
||||
try:
|
||||
bat = os.path.join(directory, 'youtube-dl-updater.bat')
|
||||
b = open(bat, 'w')
|
||||
b.write("""
|
||||
echo Updating youtube-dl...
|
||||
ping 127.0.0.1 -n 5 -w 1000 > NUL
|
||||
move /Y "%s.new" "%s"
|
||||
del "%s"
|
||||
\n""" %(exe, exe, bat))
|
||||
b.close()
|
||||
|
||||
os.startfile(bat)
|
||||
except (IOError, OSError) as err:
|
||||
sys.exit('ERROR: unable to overwrite current version')
|
||||
|
||||
sys.stderr.write(u'Done! Now you can run youtube-dl.\n')
|
||||
74
setup.py
Normal file
74
setup.py
Normal file
|
|
@ -0,0 +1,74 @@
|
|||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from __future__ import print_function
|
||||
from distutils.core import setup
|
||||
import pkg_resources
|
||||
import sys
|
||||
|
||||
try:
|
||||
import py2exe
|
||||
"""This will create an exe that needs Microsoft Visual C++ 2008 Redistributable Package"""
|
||||
except ImportError:
|
||||
if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
|
||||
print("Cannot import py2exe", file=sys.stderr)
|
||||
exit(1)
|
||||
|
||||
py2exe_options = {
|
||||
"bundle_files": 1,
|
||||
"compressed": 1,
|
||||
"optimize": 2,
|
||||
"dist_dir": '.',
|
||||
"dll_excludes": ['w9xpopen.exe']
|
||||
}
|
||||
py2exe_console = [{
|
||||
"script": "./youtube_dl/__main__.py",
|
||||
"dest_base": "youtube-dl",
|
||||
}]
|
||||
py2exe_params = {
|
||||
'console': py2exe_console,
|
||||
'options': { "py2exe": py2exe_options },
|
||||
'zipfile': None
|
||||
}
|
||||
|
||||
if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
|
||||
params = py2exe_params
|
||||
else:
|
||||
params = {
|
||||
'scripts': ['bin/youtube-dl'],
|
||||
'data_files': [('etc/bash_completion.d', ['youtube-dl.bash-completion']), # Installing system-wide would require sudo...
|
||||
('share/doc/youtube_dl', ['README.txt']),
|
||||
('share/man/man1/', ['youtube-dl.1'])]
|
||||
}
|
||||
|
||||
# Get the version from youtube_dl/version.py without importing the package
|
||||
exec(compile(open('youtube_dl/version.py').read(), 'youtube_dl/version.py', 'exec'))
|
||||
|
||||
setup(
|
||||
name = 'youtube_dl',
|
||||
version = __version__,
|
||||
description = 'YouTube video downloader',
|
||||
long_description = 'Small command-line program to download videos from YouTube.com and other video sites.',
|
||||
url = 'https://github.com/rg3/youtube-dl',
|
||||
author = 'Ricardo Garcia',
|
||||
maintainer = 'Philipp Hagemeister',
|
||||
maintainer_email = 'phihag@phihag.de',
|
||||
packages = ['youtube_dl'],
|
||||
|
||||
# Provokes warning on most systems (why?!)
|
||||
#test_suite = 'nose.collector',
|
||||
#test_requires = ['nosetest'],
|
||||
|
||||
classifiers = [
|
||||
"Topic :: Multimedia :: Video",
|
||||
"Development Status :: 5 - Production/Stable",
|
||||
"Environment :: Console",
|
||||
"License :: Public Domain",
|
||||
"Programming Language :: Python :: 2.6",
|
||||
"Programming Language :: Python :: 2.7",
|
||||
"Programming Language :: Python :: 3",
|
||||
"Programming Language :: Python :: 3.3"
|
||||
],
|
||||
|
||||
**params
|
||||
)
|
||||
|
|
@ -1 +1,40 @@
|
|||
{"username": null, "listformats": null, "skip_download": false, "usenetrc": false, "max_downloads": null, "noprogress": false, "forcethumbnail": false, "forceformat": false, "format_limit": null, "ratelimit": null, "nooverwrites": false, "forceurl": false, "writeinfojson": false, "simulate": false, "playliststart": 1, "continuedl": true, "password": null, "prefer_free_formats": false, "nopart": false, "retries": 10, "updatetime": true, "consoletitle": false, "verbose": true, "forcefilename": false, "ignoreerrors": false, "logtostderr": false, "format": null, "subtitleslang": null, "quiet": false, "outtmpl": "%(id)s.%(ext)s", "rejecttitle": null, "playlistend": -1, "writedescription": false, "forcetitle": false, "forcedescription": false, "writesubtitles": false, "matchtitle": null}
|
||||
{
|
||||
"consoletitle": false,
|
||||
"continuedl": true,
|
||||
"forcedescription": false,
|
||||
"forcefilename": false,
|
||||
"forceformat": false,
|
||||
"forcethumbnail": false,
|
||||
"forcetitle": false,
|
||||
"forceurl": false,
|
||||
"format": null,
|
||||
"format_limit": null,
|
||||
"ignoreerrors": false,
|
||||
"listformats": null,
|
||||
"logtostderr": false,
|
||||
"matchtitle": null,
|
||||
"max_downloads": null,
|
||||
"nooverwrites": false,
|
||||
"nopart": false,
|
||||
"noprogress": false,
|
||||
"outtmpl": "%(id)s.%(ext)s",
|
||||
"password": null,
|
||||
"playlistend": -1,
|
||||
"playliststart": 1,
|
||||
"prefer_free_formats": false,
|
||||
"quiet": false,
|
||||
"ratelimit": null,
|
||||
"rejecttitle": null,
|
||||
"retries": 10,
|
||||
"simulate": false,
|
||||
"skip_download": false,
|
||||
"subtitleslang": null,
|
||||
"test": true,
|
||||
"updatetime": true,
|
||||
"usenetrc": false,
|
||||
"username": null,
|
||||
"verbose": true,
|
||||
"writedescription": false,
|
||||
"writeinfojson": true,
|
||||
"writesubtitles": false
|
||||
}
|
||||
27
test/test_all_urls.py
Normal file
27
test/test_all_urls.py
Normal file
|
|
@ -0,0 +1,27 @@
|
|||
#!/usr/bin/env python
|
||||
|
||||
import sys
|
||||
import unittest
|
||||
|
||||
# Allow direct execution
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE
|
||||
|
||||
class TestAllURLsMatching(unittest.TestCase):
|
||||
def test_youtube_playlist_matching(self):
|
||||
self.assertTrue(YoutubePlaylistIE().suitable(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8'))
|
||||
self.assertTrue(YoutubePlaylistIE().suitable(u'PL63F0C78739B09958'))
|
||||
self.assertFalse(YoutubePlaylistIE().suitable(u'PLtS2H6bU1M'))
|
||||
|
||||
def test_youtube_matching(self):
|
||||
self.assertTrue(YoutubeIE().suitable(u'PLtS2H6bU1M'))
|
||||
|
||||
def test_youtube_extract(self):
|
||||
self.assertEqual(YoutubeIE()._extract_id('http://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
|
||||
self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
|
||||
self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc'), 'BaW_jenozKc')
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
|
@ -1,93 +1,125 @@
|
|||
#!/usr/bin/env python2
|
||||
import unittest
|
||||
#!/usr/bin/env python
|
||||
|
||||
import errno
|
||||
import hashlib
|
||||
import io
|
||||
import os
|
||||
import json
|
||||
import unittest
|
||||
import sys
|
||||
import hashlib
|
||||
import socket
|
||||
|
||||
from youtube_dl.FileDownloader import FileDownloader
|
||||
from youtube_dl.InfoExtractors import YoutubeIE, DailymotionIE
|
||||
from youtube_dl.InfoExtractors import MetacafeIE, BlipTVIE
|
||||
# Allow direct execution
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
import youtube_dl.FileDownloader
|
||||
import youtube_dl.InfoExtractors
|
||||
from youtube_dl.utils import *
|
||||
|
||||
DEF_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tests.json')
|
||||
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
|
||||
|
||||
# General configuration (from __init__, not very elegant...)
|
||||
jar = compat_cookiejar.CookieJar()
|
||||
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
|
||||
proxy_handler = compat_urllib_request.ProxyHandler()
|
||||
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
|
||||
compat_urllib_request.install_opener(opener)
|
||||
|
||||
def _try_rm(filename):
|
||||
""" Remove a file if it exists """
|
||||
try:
|
||||
os.remove(filename)
|
||||
except OSError as ose:
|
||||
if ose.errno != errno.ENOENT:
|
||||
raise
|
||||
|
||||
class FileDownloader(youtube_dl.FileDownloader):
|
||||
def __init__(self, *args, **kwargs):
|
||||
self.to_stderr = self.to_screen
|
||||
self.processed_info_dicts = []
|
||||
return youtube_dl.FileDownloader.__init__(self, *args, **kwargs)
|
||||
def process_info(self, info_dict):
|
||||
self.processed_info_dicts.append(info_dict)
|
||||
return youtube_dl.FileDownloader.process_info(self, info_dict)
|
||||
|
||||
def _file_md5(fn):
|
||||
with open(fn, 'rb') as f:
|
||||
return hashlib.md5(f.read()).hexdigest()
|
||||
|
||||
with io.open(DEF_FILE, encoding='utf-8') as deff:
|
||||
defs = json.load(deff)
|
||||
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
|
||||
parameters = json.load(pf)
|
||||
|
||||
|
||||
class DownloadTest(unittest.TestCase):
|
||||
PARAMETERS_FILE = "test/parameters.json"
|
||||
#calculated with md5sum:
|
||||
#md5sum (GNU coreutils) 8.19
|
||||
class TestDownload(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.parameters = parameters
|
||||
self.defs = defs
|
||||
|
||||
YOUTUBE_SIZE = 1993883
|
||||
YOUTUBE_URL = "http://www.youtube.com/watch?v=BaW_jenozKc"
|
||||
YOUTUBE_FILE = "BaW_jenozKc.mp4"
|
||||
### Dynamically generate tests
|
||||
def generator(test_case):
|
||||
|
||||
DAILYMOTION_MD5 = "d363a50e9eb4f22ce90d08d15695bb47"
|
||||
DAILYMOTION_URL = "http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech"
|
||||
DAILYMOTION_FILE = "x33vw9.mp4"
|
||||
def test_template(self):
|
||||
ie = getattr(youtube_dl.InfoExtractors, test_case['name'] + 'IE')
|
||||
if not ie._WORKING:
|
||||
print('Skipping: IE marked as not _WORKING')
|
||||
return
|
||||
if 'playlist' not in test_case and not test_case['file']:
|
||||
print('Skipping: No output file specified')
|
||||
return
|
||||
if 'skip' in test_case:
|
||||
print('Skipping: {0}'.format(test_case['skip']))
|
||||
return
|
||||
|
||||
METACAFE_SIZE = 5754305
|
||||
METACAFE_URL = "http://www.metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/"
|
||||
METACAFE_FILE = "_aUehQsCQtM.flv"
|
||||
params = self.parameters.copy()
|
||||
params.update(test_case.get('params', {}))
|
||||
|
||||
BLIP_MD5 = "93c24d2f4e0782af13b8a7606ea97ba7"
|
||||
BLIP_URL = "http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352"
|
||||
BLIP_FILE = "5779306.m4v"
|
||||
fd = FileDownloader(params)
|
||||
fd.add_info_extractor(ie())
|
||||
for ien in test_case.get('add_ie', []):
|
||||
fd.add_info_extractor(getattr(youtube_dl.InfoExtractors, ien + 'IE')())
|
||||
|
||||
XVIDEO_MD5 = ""
|
||||
XVIDEO_URL = ""
|
||||
XVIDEO_FILE = ""
|
||||
test_cases = test_case.get('playlist', [test_case])
|
||||
for tc in test_cases:
|
||||
_try_rm(tc['file'])
|
||||
_try_rm(tc['file'] + '.part')
|
||||
_try_rm(tc['file'] + '.info.json')
|
||||
try:
|
||||
fd.download([test_case['url']])
|
||||
|
||||
for tc in test_cases:
|
||||
if not test_case.get('params', {}).get('skip_download', False):
|
||||
self.assertTrue(os.path.exists(tc['file']))
|
||||
self.assertTrue(os.path.exists(tc['file'] + '.info.json'))
|
||||
if 'md5' in tc:
|
||||
md5_for_file = _file_md5(tc['file'])
|
||||
self.assertEqual(md5_for_file, tc['md5'])
|
||||
with io.open(tc['file'] + '.info.json', encoding='utf-8') as infof:
|
||||
info_dict = json.load(infof)
|
||||
for (info_field, value) in tc.get('info_dict', {}).items():
|
||||
if value.startswith('md5:'):
|
||||
md5_info_value = hashlib.md5(info_dict.get(info_field, '')).hexdigest()
|
||||
self.assertEqual(value[3:], md5_info_value)
|
||||
else:
|
||||
self.assertEqual(value, info_dict.get(info_field))
|
||||
finally:
|
||||
for tc in test_cases:
|
||||
_try_rm(tc['file'])
|
||||
_try_rm(tc['file'] + '.part')
|
||||
_try_rm(tc['file'] + '.info.json')
|
||||
|
||||
return test_template
|
||||
|
||||
### And add them to TestDownload
|
||||
for test_case in defs:
|
||||
test_method = generator(test_case)
|
||||
test_method.__name__ = "test_{0}".format(test_case["name"])
|
||||
setattr(TestDownload, test_method.__name__, test_method)
|
||||
del test_method
|
||||
|
||||
|
||||
def test_youtube(self):
|
||||
#let's download a file from youtube
|
||||
with open(DownloadTest.PARAMETERS_FILE) as f:
|
||||
fd = FileDownloader(json.load(f))
|
||||
fd.add_info_extractor(YoutubeIE())
|
||||
fd.download([DownloadTest.YOUTUBE_URL])
|
||||
self.assertTrue(os.path.exists(DownloadTest.YOUTUBE_FILE))
|
||||
self.assertEqual(os.path.getsize(DownloadTest.YOUTUBE_FILE), DownloadTest.YOUTUBE_SIZE)
|
||||
|
||||
def test_dailymotion(self):
|
||||
with open(DownloadTest.PARAMETERS_FILE) as f:
|
||||
fd = FileDownloader(json.load(f))
|
||||
fd.add_info_extractor(DailymotionIE())
|
||||
fd.download([DownloadTest.DAILYMOTION_URL])
|
||||
self.assertTrue(os.path.exists(DownloadTest.DAILYMOTION_FILE))
|
||||
md5_down_file = md5_for_file(DownloadTest.DAILYMOTION_FILE)
|
||||
self.assertEqual(md5_down_file, DownloadTest.DAILYMOTION_MD5)
|
||||
|
||||
def test_metacafe(self):
|
||||
#this emulate a skip,to be 2.6 compatible
|
||||
with open(DownloadTest.PARAMETERS_FILE) as f:
|
||||
fd = FileDownloader(json.load(f))
|
||||
fd.add_info_extractor(MetacafeIE())
|
||||
fd.add_info_extractor(YoutubeIE())
|
||||
fd.download([DownloadTest.METACAFE_URL])
|
||||
self.assertTrue(os.path.exists(DownloadTest.METACAFE_FILE))
|
||||
self.assertEqual(os.path.getsize(DownloadTest.METACAFE_FILE), DownloadTest.METACAFE_SIZE)
|
||||
|
||||
def test_blip(self):
|
||||
with open(DownloadTest.PARAMETERS_FILE) as f:
|
||||
fd = FileDownloader(json.load(f))
|
||||
fd.add_info_extractor(BlipTVIE())
|
||||
fd.download([DownloadTest.BLIP_URL])
|
||||
self.assertTrue(os.path.exists(DownloadTest.BLIP_FILE))
|
||||
md5_down_file = md5_for_file(DownloadTest.BLIP_FILE)
|
||||
self.assertEqual(md5_down_file, DownloadTest.BLIP_MD5)
|
||||
|
||||
def tearDown(self):
|
||||
if os.path.exists(DownloadTest.YOUTUBE_FILE):
|
||||
os.remove(DownloadTest.YOUTUBE_FILE)
|
||||
if os.path.exists(DownloadTest.DAILYMOTION_FILE):
|
||||
os.remove(DownloadTest.DAILYMOTION_FILE)
|
||||
if os.path.exists(DownloadTest.METACAFE_FILE):
|
||||
os.remove(DownloadTest.METACAFE_FILE)
|
||||
if os.path.exists(DownloadTest.BLIP_FILE):
|
||||
os.remove(DownloadTest.BLIP_FILE)
|
||||
|
||||
def md5_for_file(filename, block_size=2**20):
|
||||
with open(filename) as f:
|
||||
md5 = hashlib.md5()
|
||||
while True:
|
||||
data = f.read(block_size)
|
||||
if not data:
|
||||
break
|
||||
md5.update(data)
|
||||
return md5.hexdigest()
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
|
|
|||
26
test/test_execution.py
Normal file
26
test/test_execution.py
Normal file
|
|
@ -0,0 +1,26 @@
|
|||
import unittest
|
||||
|
||||
import sys
|
||||
import os
|
||||
import subprocess
|
||||
|
||||
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||||
|
||||
try:
|
||||
_DEV_NULL = subprocess.DEVNULL
|
||||
except AttributeError:
|
||||
_DEV_NULL = open(os.devnull, 'wb')
|
||||
|
||||
class TestExecution(unittest.TestCase):
|
||||
def test_import(self):
|
||||
subprocess.check_call([sys.executable, '-c', 'import youtube_dl'], cwd=rootDir)
|
||||
|
||||
def test_module_exec(self):
|
||||
if sys.version_info >= (2,7): # Python 2.6 doesn't support package execution
|
||||
subprocess.check_call([sys.executable, '-m', 'youtube_dl', '--version'], cwd=rootDir, stdout=_DEV_NULL)
|
||||
|
||||
def test_main_exec(self):
|
||||
subprocess.check_call([sys.executable, 'youtube_dl/__main__.py', '--version'], cwd=rootDir, stdout=_DEV_NULL)
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
|
@ -1,15 +1,25 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Various small unit tests
|
||||
|
||||
import sys
|
||||
import unittest
|
||||
|
||||
# Allow direct execution
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
#from youtube_dl.utils import htmlentity_transform
|
||||
from youtube_dl.utils import timeconvert
|
||||
from youtube_dl.utils import sanitize_filename
|
||||
from youtube_dl.utils import unescapeHTML
|
||||
from youtube_dl.utils import orderedSet
|
||||
|
||||
if sys.version_info < (3, 0):
|
||||
_compat_str = lambda b: b.decode('unicode-escape')
|
||||
else:
|
||||
_compat_str = lambda s: s
|
||||
|
||||
|
||||
class TestUtil(unittest.TestCase):
|
||||
def test_timeconvert(self):
|
||||
|
|
@ -17,24 +27,64 @@ def test_timeconvert(self):
|
|||
self.assertTrue(timeconvert('bougrg') is None)
|
||||
|
||||
def test_sanitize_filename(self):
|
||||
self.assertEqual(sanitize_filename(u'abc'), u'abc')
|
||||
self.assertEqual(sanitize_filename(u'abc_d-e'), u'abc_d-e')
|
||||
self.assertEqual(sanitize_filename('abc'), 'abc')
|
||||
self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
|
||||
|
||||
self.assertEqual(sanitize_filename(u'123'), u'123')
|
||||
self.assertEqual(sanitize_filename('123'), '123')
|
||||
|
||||
self.assertEqual(u'abc-de', sanitize_filename(u'abc/de'))
|
||||
self.assertFalse(u'/' in sanitize_filename(u'abc/de///'))
|
||||
self.assertEqual('abc_de', sanitize_filename('abc/de'))
|
||||
self.assertFalse('/' in sanitize_filename('abc/de///'))
|
||||
|
||||
self.assertEqual(u'abc-de', sanitize_filename(u'abc/<>\\*|de'))
|
||||
self.assertEqual(u'xxx', sanitize_filename(u'xxx/<>\\*|'))
|
||||
self.assertEqual(u'yes no', sanitize_filename(u'yes? no'))
|
||||
self.assertEqual(u'this - that', sanitize_filename(u'this: that'))
|
||||
self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
|
||||
self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
|
||||
self.assertEqual('yes no', sanitize_filename('yes? no'))
|
||||
self.assertEqual('this - that', sanitize_filename('this: that'))
|
||||
|
||||
self.assertEqual(sanitize_filename(u'ä'), u'ä')
|
||||
self.assertEqual(sanitize_filename(u'кириллица'), u'кириллица')
|
||||
self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
|
||||
aumlaut = _compat_str('\xe4')
|
||||
self.assertEqual(sanitize_filename(aumlaut), aumlaut)
|
||||
tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
|
||||
self.assertEqual(sanitize_filename(tests), tests)
|
||||
|
||||
for forbidden in u'"\0\\/':
|
||||
self.assertTrue(forbidden not in sanitize_filename(forbidden))
|
||||
forbidden = '"\0\\/'
|
||||
for fc in forbidden:
|
||||
for fbc in forbidden:
|
||||
self.assertTrue(fbc not in sanitize_filename(fc))
|
||||
|
||||
def test_sanitize_filename_restricted(self):
|
||||
self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
|
||||
self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
|
||||
|
||||
self.assertEqual(sanitize_filename('123', restricted=True), '123')
|
||||
|
||||
self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
|
||||
self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
|
||||
|
||||
self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
|
||||
self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
|
||||
self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
|
||||
self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
|
||||
|
||||
tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
|
||||
self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
|
||||
self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename
|
||||
|
||||
forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
|
||||
for fc in forbidden:
|
||||
for fbc in forbidden:
|
||||
self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
|
||||
|
||||
# Handle a common case more neatly
|
||||
self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
|
||||
self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
|
||||
# .. but make sure the file name is never empty
|
||||
self.assertTrue(sanitize_filename('-', restricted=True) != '')
|
||||
self.assertTrue(sanitize_filename(':', restricted=True) != '')
|
||||
|
||||
def test_sanitize_ids(self):
|
||||
self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
|
||||
self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
|
||||
self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
|
||||
|
||||
def test_ordered_set(self):
|
||||
self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
|
||||
|
|
@ -44,4 +94,7 @@ def test_ordered_set(self):
|
|||
self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
|
||||
|
||||
def test_unescape_html(self):
|
||||
self.assertEqual(unescapeHTML(u"%20;"), u"%20;")
|
||||
self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
|
|
|||
77
test/test_write_info_json.py
Normal file
77
test/test_write_info_json.py
Normal file
|
|
@ -0,0 +1,77 @@
|
|||
#!/usr/bin/env python
|
||||
# coding: utf-8
|
||||
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import unittest
|
||||
|
||||
# Allow direct execution
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
import youtube_dl.FileDownloader
|
||||
import youtube_dl.InfoExtractors
|
||||
from youtube_dl.utils import *
|
||||
|
||||
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
|
||||
|
||||
# General configuration (from __init__, not very elegant...)
|
||||
jar = compat_cookiejar.CookieJar()
|
||||
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
|
||||
proxy_handler = compat_urllib_request.ProxyHandler()
|
||||
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
|
||||
compat_urllib_request.install_opener(opener)
|
||||
|
||||
class FileDownloader(youtube_dl.FileDownloader):
|
||||
def __init__(self, *args, **kwargs):
|
||||
youtube_dl.FileDownloader.__init__(self, *args, **kwargs)
|
||||
self.to_stderr = self.to_screen
|
||||
|
||||
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
|
||||
params = json.load(pf)
|
||||
params['writeinfojson'] = True
|
||||
params['skip_download'] = True
|
||||
params['writedescription'] = True
|
||||
|
||||
TEST_ID = 'BaW_jenozKc'
|
||||
INFO_JSON_FILE = TEST_ID + '.mp4.info.json'
|
||||
DESCRIPTION_FILE = TEST_ID + '.mp4.description'
|
||||
EXPECTED_DESCRIPTION = u'''test chars: "'/\ä↭𝕐
|
||||
|
||||
This is a test video for youtube-dl.
|
||||
|
||||
For more information, contact phihag@phihag.de .'''
|
||||
|
||||
class TestInfoJSON(unittest.TestCase):
|
||||
def setUp(self):
|
||||
# Clear old files
|
||||
self.tearDown()
|
||||
|
||||
def test_info_json(self):
|
||||
ie = youtube_dl.InfoExtractors.YoutubeIE()
|
||||
fd = FileDownloader(params)
|
||||
fd.add_info_extractor(ie)
|
||||
fd.download([TEST_ID])
|
||||
self.assertTrue(os.path.exists(INFO_JSON_FILE))
|
||||
with io.open(INFO_JSON_FILE, 'r', encoding='utf-8') as jsonf:
|
||||
jd = json.load(jsonf)
|
||||
self.assertEqual(jd['upload_date'], u'20121002')
|
||||
self.assertEqual(jd['description'], EXPECTED_DESCRIPTION)
|
||||
self.assertEqual(jd['id'], TEST_ID)
|
||||
self.assertEqual(jd['extractor'], 'youtube')
|
||||
self.assertEqual(jd['title'], u'''youtube-dl test video "'/\ä↭𝕐''')
|
||||
self.assertEqual(jd['uploader'], 'Philipp Hagemeister')
|
||||
|
||||
self.assertTrue(os.path.exists(DESCRIPTION_FILE))
|
||||
with io.open(DESCRIPTION_FILE, 'r', encoding='utf-8') as descf:
|
||||
descr = descf.read()
|
||||
self.assertEqual(descr, EXPECTED_DESCRIPTION)
|
||||
|
||||
def tearDown(self):
|
||||
if os.path.exists(INFO_JSON_FILE):
|
||||
os.remove(INFO_JSON_FILE)
|
||||
if os.path.exists(DESCRIPTION_FILE):
|
||||
os.remove(DESCRIPTION_FILE)
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
73
test/test_youtube_lists.py
Normal file
73
test/test_youtube_lists.py
Normal file
|
|
@ -0,0 +1,73 @@
|
|||
#!/usr/bin/env python
|
||||
|
||||
import sys
|
||||
import unittest
|
||||
import json
|
||||
|
||||
# Allow direct execution
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from youtube_dl.InfoExtractors import YoutubeUserIE,YoutubePlaylistIE
|
||||
from youtube_dl.utils import *
|
||||
|
||||
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
|
||||
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
|
||||
parameters = json.load(pf)
|
||||
|
||||
# General configuration (from __init__, not very elegant...)
|
||||
jar = compat_cookiejar.CookieJar()
|
||||
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
|
||||
proxy_handler = compat_urllib_request.ProxyHandler()
|
||||
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
|
||||
compat_urllib_request.install_opener(opener)
|
||||
|
||||
class FakeDownloader(object):
|
||||
def __init__(self):
|
||||
self.result = []
|
||||
self.params = parameters
|
||||
def to_screen(self, s):
|
||||
print(s)
|
||||
def trouble(self, s):
|
||||
raise Exception(s)
|
||||
def download(self, x):
|
||||
self.result.append(x)
|
||||
|
||||
class TestYoutubeLists(unittest.TestCase):
|
||||
def test_youtube_playlist(self):
|
||||
DL = FakeDownloader()
|
||||
IE = YoutubePlaylistIE(DL)
|
||||
IE.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
|
||||
self.assertEqual(DL.result, [
|
||||
['http://www.youtube.com/watch?v=bV9L5Ht9LgY'],
|
||||
['http://www.youtube.com/watch?v=FXxLjLQi3Fg'],
|
||||
['http://www.youtube.com/watch?v=tU3Bgo5qJZE']
|
||||
])
|
||||
|
||||
def test_youtube_playlist_long(self):
|
||||
DL = FakeDownloader()
|
||||
IE = YoutubePlaylistIE(DL)
|
||||
IE.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
|
||||
self.assertTrue(len(DL.result) >= 799)
|
||||
|
||||
def test_youtube_course(self):
|
||||
DL = FakeDownloader()
|
||||
IE = YoutubePlaylistIE(DL)
|
||||
# TODO find a > 100 (paginating?) videos course
|
||||
IE.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
|
||||
self.assertEqual(DL.result[0], ['http://www.youtube.com/watch?v=j9WZyLZCBzs'])
|
||||
self.assertEqual(len(DL.result), 25)
|
||||
self.assertEqual(DL.result[-1], ['http://www.youtube.com/watch?v=rYefUsYuEp0'])
|
||||
|
||||
def test_youtube_channel(self):
|
||||
# I give up, please find a channel that does paginate and test this like test_youtube_playlist_long
|
||||
pass # TODO
|
||||
|
||||
def test_youtube_user(self):
|
||||
DL = FakeDownloader()
|
||||
IE = YoutubeUserIE(DL)
|
||||
IE.extract('https://www.youtube.com/user/TheLinuxFoundation')
|
||||
self.assertTrue(len(DL.result) >= 320)
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
57
test/test_youtube_subtitles.py
Normal file
57
test/test_youtube_subtitles.py
Normal file
|
|
@ -0,0 +1,57 @@
|
|||
#!/usr/bin/env python
|
||||
|
||||
import sys
|
||||
import unittest
|
||||
import json
|
||||
import io
|
||||
import hashlib
|
||||
|
||||
# Allow direct execution
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from youtube_dl.InfoExtractors import YoutubeIE
|
||||
from youtube_dl.utils import *
|
||||
|
||||
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
|
||||
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
|
||||
parameters = json.load(pf)
|
||||
|
||||
# General configuration (from __init__, not very elegant...)
|
||||
jar = compat_cookiejar.CookieJar()
|
||||
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
|
||||
proxy_handler = compat_urllib_request.ProxyHandler()
|
||||
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
|
||||
compat_urllib_request.install_opener(opener)
|
||||
|
||||
class FakeDownloader(object):
|
||||
def __init__(self):
|
||||
self.result = []
|
||||
self.params = parameters
|
||||
def to_screen(self, s):
|
||||
print(s)
|
||||
def trouble(self, s):
|
||||
raise Exception(s)
|
||||
def download(self, x):
|
||||
self.result.append(x)
|
||||
|
||||
md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
|
||||
|
||||
class TestYoutubeSubtitles(unittest.TestCase):
|
||||
def test_youtube_subtitles(self):
|
||||
DL = FakeDownloader()
|
||||
DL.params['writesubtitles'] = True
|
||||
IE = YoutubeIE(DL)
|
||||
info_dict = IE.extract('QRS8MkLhQmM')
|
||||
self.assertEqual(md5(info_dict[0]['subtitles']), 'c3228550d59116f3c29fba370b55d033')
|
||||
|
||||
def test_youtube_subtitles_it(self):
|
||||
DL = FakeDownloader()
|
||||
DL.params['writesubtitles'] = True
|
||||
DL.params['subtitleslang'] = 'it'
|
||||
IE = YoutubeIE(DL)
|
||||
info_dict = IE.extract('QRS8MkLhQmM')
|
||||
self.assertEqual(md5(info_dict[0]['subtitles']), '132a88a0daf8e1520f393eb58f1f646a')
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
164
test/tests.json
Normal file
164
test/tests.json
Normal file
|
|
@ -0,0 +1,164 @@
|
|||
[
|
||||
{
|
||||
"name": "Youtube",
|
||||
"url": "http://www.youtube.com/watch?v=BaW_jenozKc",
|
||||
"file": "BaW_jenozKc.mp4",
|
||||
"info_dict": {
|
||||
"title": "youtube-dl test video \"'/\\ä↭𝕐",
|
||||
"uploader": "Philipp Hagemeister",
|
||||
"uploader_id": "phihag",
|
||||
"upload_date": "20121002",
|
||||
"description": "test chars: \"'/\\ä↭𝕐\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ."
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Dailymotion",
|
||||
"md5": "392c4b85a60a90dc4792da41ce3144eb",
|
||||
"url": "http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech",
|
||||
"file": "x33vw9.mp4"
|
||||
},
|
||||
{
|
||||
"name": "Metacafe",
|
||||
"add_ie": ["Youtube"],
|
||||
"url": "http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
|
||||
"file": "_aUehQsCQtM.flv"
|
||||
},
|
||||
{
|
||||
"name": "BlipTV",
|
||||
"md5": "b2d849efcf7ee18917e4b4d9ff37cafe",
|
||||
"url": "http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352",
|
||||
"file": "5779306.m4v"
|
||||
},
|
||||
{
|
||||
"name": "XVideos",
|
||||
"md5": "1d0c835822f0a71a7bf011855db929d0",
|
||||
"url": "http://www.xvideos.com/video939581/funny_porns_by_s_-1",
|
||||
"file": "939581.flv"
|
||||
},
|
||||
{
|
||||
"name": "Vimeo",
|
||||
"md5": "8879b6cc097e987f02484baf890129e5",
|
||||
"url": "http://vimeo.com/56015672",
|
||||
"file": "56015672.mp4",
|
||||
"info_dict": {
|
||||
"title": "youtube-dl test video - ★ \" ' 幸 / \\ ä ↭ 𝕐",
|
||||
"uploader": "Filippo Valsorda",
|
||||
"uploader_id": "user7108434",
|
||||
"upload_date": "20121220",
|
||||
"description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: ★ \" ' 幸 / \\ ä ↭ 𝕐"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Soundcloud",
|
||||
"md5": "ebef0a451b909710ed1d7787dddbf0d7",
|
||||
"url": "http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy",
|
||||
"file": "62986583.mp3"
|
||||
},
|
||||
{
|
||||
"name": "StanfordOpenClassroom",
|
||||
"md5": "544a9468546059d4e80d76265b0443b8",
|
||||
"url": "http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100",
|
||||
"file": "PracticalUnix_intro-environment.mp4"
|
||||
},
|
||||
{
|
||||
"name": "XNXX",
|
||||
"md5": "0831677e2b4761795f68d417e0b7b445",
|
||||
"url": "http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_",
|
||||
"file": "1135332.flv"
|
||||
},
|
||||
{
|
||||
"name": "Youku",
|
||||
"url": "http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
|
||||
"file": "XNDgyMDQ2NTQw_part00.flv",
|
||||
"md5": "ffe3f2e435663dc2d1eea34faeff5b5b",
|
||||
"params": { "test": false }
|
||||
},
|
||||
{
|
||||
"name": "NBA",
|
||||
"url": "http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html",
|
||||
"file": "0021200253-okc-bkn-recap.nba.mp4",
|
||||
"md5": "c0edcfc37607344e2ff8f13c378c88a4"
|
||||
},
|
||||
{
|
||||
"name": "JustinTV",
|
||||
"url": "http://www.twitch.tv/thegamedevhub/b/296128360",
|
||||
"file": "296128360.flv",
|
||||
"md5": "ecaa8a790c22a40770901460af191c9a"
|
||||
},
|
||||
{
|
||||
"name": "MyVideo",
|
||||
"url": "http://www.myvideo.de/watch/8229274/bowling_fail_or_win",
|
||||
"file": "8229274.flv",
|
||||
"md5": "2d2753e8130479ba2cb7e0a37002053e"
|
||||
},
|
||||
{
|
||||
"name": "Escapist",
|
||||
"url": "http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate",
|
||||
"file": "6618-Breaking-Down-Baldurs-Gate.flv",
|
||||
"md5": "c6793dbda81388f4264c1ba18684a74d",
|
||||
"skip": "Fails with timeout on Travis"
|
||||
},
|
||||
{
|
||||
"name": "GooglePlus",
|
||||
"url": "https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
|
||||
"file": "ZButuJc6CtH.flv"
|
||||
},
|
||||
{
|
||||
"name": "FunnyOrDie",
|
||||
"url": "http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version",
|
||||
"file": "0732f586d7.mp4",
|
||||
"md5": "f647e9e90064b53b6e046e75d0241fbd"
|
||||
},
|
||||
{
|
||||
"name": "TweetReel",
|
||||
"url": "http://tweetreel.com/?77smq",
|
||||
"file": "77smq.mov",
|
||||
"md5": "56b4d9ca9de467920f3f99a6d91255d6",
|
||||
"info_dict": {
|
||||
"uploader": "itszero",
|
||||
"uploader_id": "itszero",
|
||||
"upload_date": "20091225",
|
||||
"description": "Installing Gentoo Linux on Powerbook G4, it turns out the sleep indicator becomes HDD activity indicator :D"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Steam",
|
||||
"url": "http://store.steampowered.com/video/105600/",
|
||||
"playlist": [
|
||||
{
|
||||
"file": "81300.flv",
|
||||
"md5": "f870007cee7065d7c76b88f0a45ecc07",
|
||||
"info_dict": {
|
||||
"title": "Terraria 1.1 Trailer"
|
||||
}
|
||||
},
|
||||
{
|
||||
"file": "80859.flv",
|
||||
"md5": "61aaf31a5c5c3041afb58fb83cbb5751",
|
||||
"info_dict": {
|
||||
"title": "Terraria Trailer"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "Ustream",
|
||||
"url": "http://www.ustream.tv/recorded/20274954",
|
||||
"file": "20274954.flv",
|
||||
"md5": "088f151799e8f572f84eb62f17d73e5c",
|
||||
"info_dict": {
|
||||
"title": "Young Americans for Liberty February 7, 2012 2:28 AM"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "InfoQ",
|
||||
"url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
|
||||
"file": "12-jan-pythonthings.mp4",
|
||||
"info_dict": {
|
||||
"title": "A Few of My Favorite [Python] Things"
|
||||
},
|
||||
"params": {
|
||||
"skip_download": true
|
||||
}
|
||||
}
|
||||
]
|
||||
BIN
youtube-dl
Executable file
BIN
youtube-dl
Executable file
Binary file not shown.
|
|
@ -1,14 +0,0 @@
|
|||
__youtube-dl()
|
||||
{
|
||||
local cur prev opts
|
||||
COMPREPLY=()
|
||||
cur="${COMP_WORDS[COMP_CWORD]}"
|
||||
opts="--all-formats --audio-format --audio-quality --auto-number --batch-file --console-title --continue --cookies --dump-user-agent --extract-audio --format --get-description --get-filename --get-format --get-thumbnail --get-title --get-url --help --id --ignore-errors --keep-video --list-extractors --list-formats --literal --match-title --max-downloads --max-quality --netrc --no-continue --no-mtime --no-overwrites --no-part --no-progress --output --password --playlist-end --playlist-start --prefer-free-formats --quiet --rate-limit --reject-title --retries --simulate --skip-download --srt-lang --title --update --user-agent --username --verbose --version --write-description --write-info-json --write-srt"
|
||||
|
||||
if [[ ${cur} == * ]] ; then
|
||||
COMPREPLY=( $(compgen -W "${opts}" -- ${cur}) )
|
||||
return 0
|
||||
fi
|
||||
}
|
||||
|
||||
complete -F __youtube-dl youtube-dl
|
||||
BIN
youtube-dl.exe
Normal file
BIN
youtube-dl.exe
Normal file
Binary file not shown.
|
|
@ -1,20 +1,22 @@
|
|||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import httplib
|
||||
from __future__ import absolute_import
|
||||
|
||||
import math
|
||||
import io
|
||||
import os
|
||||
import re
|
||||
import socket
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
import urllib2
|
||||
import traceback
|
||||
|
||||
if os.name == 'nt':
|
||||
import ctypes
|
||||
|
||||
from utils import *
|
||||
from .utils import *
|
||||
|
||||
|
||||
class FileDownloader(object):
|
||||
|
|
@ -57,10 +59,13 @@ class FileDownloader(object):
|
|||
format: Video format code.
|
||||
format_limit: Highest quality format to try.
|
||||
outtmpl: Template for output names.
|
||||
restrictfilenames: Do not allow "&" and spaces in file names
|
||||
ignoreerrors: Do not stop on download errors.
|
||||
ratelimit: Download speed limit, in bytes/sec.
|
||||
nooverwrites: Prevent overwriting files.
|
||||
retries: Number of times to retry for HTTP error 5xx
|
||||
buffersize: Size of download buffer in bytes.
|
||||
noresizebuffer: Do not automatically resize the download buffer.
|
||||
continuedl: Try to continue downloads if possible.
|
||||
noprogress: Do not print the progress bar.
|
||||
playliststart: Playlist item to start at.
|
||||
|
|
@ -75,6 +80,7 @@ class FileDownloader(object):
|
|||
writeinfojson: Write the video description to a .info.json file
|
||||
writesubtitles: Write the video subtitles to a .srt file
|
||||
subtitleslang: Language of the subtitles to download
|
||||
test: Download only first bytes to test the downloader.
|
||||
"""
|
||||
|
||||
params = None
|
||||
|
|
@ -93,6 +99,9 @@ def __init__(self, params):
|
|||
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
|
||||
self.params = params
|
||||
|
||||
if '%(stitle)s' in self.params['outtmpl']:
|
||||
self.to_stderr(u'WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
|
||||
|
||||
@staticmethod
|
||||
def format_bytes(bytes):
|
||||
if bytes is None:
|
||||
|
|
@ -102,7 +111,7 @@ def format_bytes(bytes):
|
|||
if bytes == 0.0:
|
||||
exponent = 0
|
||||
else:
|
||||
exponent = long(math.log(bytes, 1024.0))
|
||||
exponent = int(math.log(bytes, 1024.0))
|
||||
suffix = 'bkMGTPEZY'[exponent]
|
||||
converted = float(bytes) / float(1024 ** exponent)
|
||||
return '%.2f%s' % (converted, suffix)
|
||||
|
|
@ -121,7 +130,7 @@ def calc_eta(start, now, total, current):
|
|||
if current == 0 or dif < 0.001: # One millisecond
|
||||
return '--:--'
|
||||
rate = float(current) / dif
|
||||
eta = long((float(total) - float(current)) / rate)
|
||||
eta = int((float(total) - float(current)) / rate)
|
||||
(eta_mins, eta_secs) = divmod(eta, 60)
|
||||
if eta_mins > 99:
|
||||
return '--:--'
|
||||
|
|
@ -139,23 +148,23 @@ def best_block_size(elapsed_time, bytes):
|
|||
new_min = max(bytes / 2.0, 1.0)
|
||||
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
|
||||
if elapsed_time < 0.001:
|
||||
return long(new_max)
|
||||
return int(new_max)
|
||||
rate = bytes / elapsed_time
|
||||
if rate > new_max:
|
||||
return long(new_max)
|
||||
return int(new_max)
|
||||
if rate < new_min:
|
||||
return long(new_min)
|
||||
return long(rate)
|
||||
return int(new_min)
|
||||
return int(rate)
|
||||
|
||||
@staticmethod
|
||||
def parse_bytes(bytestr):
|
||||
"""Parse a string indicating a byte quantity into a long integer."""
|
||||
"""Parse a string indicating a byte quantity into an integer."""
|
||||
matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
|
||||
if matchobj is None:
|
||||
return None
|
||||
number = float(matchobj.group(1))
|
||||
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
|
||||
return long(round(number * multiplier))
|
||||
return int(round(number * multiplier))
|
||||
|
||||
def add_info_extractor(self, ie):
|
||||
"""Add an InfoExtractor object to the end of the list."""
|
||||
|
|
@ -173,14 +182,18 @@ def to_screen(self, message, skip_eol=False):
|
|||
if not self.params.get('quiet', False):
|
||||
terminator = [u'\n', u''][skip_eol]
|
||||
output = message + terminator
|
||||
if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
|
||||
if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
|
||||
output = output.encode(preferredencoding(), 'ignore')
|
||||
self._screen_file.write(output)
|
||||
self._screen_file.flush()
|
||||
|
||||
def to_stderr(self, message):
|
||||
"""Print message to stderr."""
|
||||
print >>sys.stderr, message.encode(preferredencoding())
|
||||
assert type(message) == type(u'')
|
||||
output = message + u'\n'
|
||||
if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
|
||||
output = output.encode(preferredencoding())
|
||||
sys.stderr.write(output)
|
||||
|
||||
def to_cons_title(self, message):
|
||||
"""Set console/terminal window title to message."""
|
||||
|
|
@ -195,17 +208,24 @@ def to_cons_title(self, message):
|
|||
|
||||
def fixed_template(self):
|
||||
"""Checks if the output template is fixed."""
|
||||
return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
|
||||
return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None)
|
||||
|
||||
def trouble(self, message=None):
|
||||
def trouble(self, message=None, tb=None):
|
||||
"""Determine action to take when a download problem appears.
|
||||
|
||||
Depending on if the downloader has been configured to ignore
|
||||
download errors or not, this method may throw an exception or
|
||||
not when errors are found, after printing the message.
|
||||
|
||||
tb, if given, is additional traceback information.
|
||||
"""
|
||||
if message is not None:
|
||||
self.to_stderr(message)
|
||||
if self.params.get('verbose'):
|
||||
if tb is None:
|
||||
tb_data = traceback.format_list(traceback.extract_stack())
|
||||
tb = u''.join(tb_data)
|
||||
self.to_stderr(tb)
|
||||
if not self.params.get('ignoreerrors', False):
|
||||
raise DownloadError(message)
|
||||
self._download_retcode = 1
|
||||
|
|
@ -240,7 +260,7 @@ def try_rename(self, old_filename, new_filename):
|
|||
if old_filename == new_filename:
|
||||
return
|
||||
os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
|
||||
except (IOError, OSError), err:
|
||||
except (IOError, OSError) as err:
|
||||
self.trouble(u'ERROR: unable to rename file')
|
||||
|
||||
def try_utime(self, filename, last_modified_hdr):
|
||||
|
|
@ -298,7 +318,7 @@ def report_file_already_downloaded(self, file_name):
|
|||
"""Report file has already been fully downloaded."""
|
||||
try:
|
||||
self.to_screen(u'[download] %s has already been downloaded' % file_name)
|
||||
except (UnicodeEncodeError), err:
|
||||
except (UnicodeEncodeError) as err:
|
||||
self.to_screen(u'[download] The file has already been downloaded')
|
||||
|
||||
def report_unable_to_resume(self):
|
||||
|
|
@ -320,11 +340,19 @@ def prepare_filename(self, info_dict):
|
|||
"""Generate the output filename."""
|
||||
try:
|
||||
template_dict = dict(info_dict)
|
||||
template_dict['epoch'] = unicode(long(time.time()))
|
||||
template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
|
||||
|
||||
template_dict['epoch'] = int(time.time())
|
||||
template_dict['autonumber'] = u'%05d' % self._num_downloads
|
||||
|
||||
sanitize = lambda k,v: sanitize_filename(
|
||||
u'NA' if v is None else compat_str(v),
|
||||
restricted=self.params.get('restrictfilenames'),
|
||||
is_id=(k==u'id'))
|
||||
template_dict = dict((k, sanitize(k, v)) for k,v in template_dict.items())
|
||||
|
||||
filename = self.params['outtmpl'] % template_dict
|
||||
return filename
|
||||
except (ValueError, KeyError), err:
|
||||
except (ValueError, KeyError) as err:
|
||||
self.trouble(u'ERROR: invalid system charset or erroneous output template')
|
||||
return None
|
||||
|
||||
|
|
@ -347,7 +375,11 @@ def _match_entry(self, info_dict):
|
|||
def process_info(self, info_dict):
|
||||
"""Process a single dictionary returned by an InfoExtractor."""
|
||||
|
||||
info_dict['stitle'] = sanitize_filename(info_dict['title'])
|
||||
# Keep for backwards compatibility
|
||||
info_dict['stitle'] = info_dict['title']
|
||||
|
||||
if not 'format' in info_dict:
|
||||
info_dict['format'] = info_dict['ext']
|
||||
|
||||
reason = self._match_entry(info_dict)
|
||||
if reason is not None:
|
||||
|
|
@ -363,17 +395,17 @@ def process_info(self, info_dict):
|
|||
|
||||
# Forced printings
|
||||
if self.params.get('forcetitle', False):
|
||||
print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
|
||||
compat_print(info_dict['title'])
|
||||
if self.params.get('forceurl', False):
|
||||
print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
|
||||
compat_print(info_dict['url'])
|
||||
if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
|
||||
print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
|
||||
compat_print(info_dict['thumbnail'])
|
||||
if self.params.get('forcedescription', False) and 'description' in info_dict:
|
||||
print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
|
||||
compat_print(info_dict['description'])
|
||||
if self.params.get('forcefilename', False) and filename is not None:
|
||||
print filename.encode(preferredencoding(), 'xmlcharrefreplace')
|
||||
compat_print(filename)
|
||||
if self.params.get('forceformat', False):
|
||||
print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')
|
||||
compat_print(info_dict['format'])
|
||||
|
||||
# Do nothing else if in simulate mode
|
||||
if self.params.get('simulate', False):
|
||||
|
|
@ -386,19 +418,16 @@ def process_info(self, info_dict):
|
|||
dn = os.path.dirname(encodeFilename(filename))
|
||||
if dn != '' and not os.path.exists(dn): # dn is already encoded
|
||||
os.makedirs(dn)
|
||||
except (OSError, IOError), err:
|
||||
self.trouble(u'ERROR: unable to create directory ' + unicode(err))
|
||||
except (OSError, IOError) as err:
|
||||
self.trouble(u'ERROR: unable to create directory ' + compat_str(err))
|
||||
return
|
||||
|
||||
if self.params.get('writedescription', False):
|
||||
try:
|
||||
descfn = filename + u'.description'
|
||||
self.report_writedescription(descfn)
|
||||
descfile = open(encodeFilename(descfn), 'wb')
|
||||
try:
|
||||
descfile.write(info_dict['description'].encode('utf-8'))
|
||||
finally:
|
||||
descfile.close()
|
||||
with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
|
||||
descfile.write(info_dict['description'])
|
||||
except (OSError, IOError):
|
||||
self.trouble(u'ERROR: Cannot write description file ' + descfn)
|
||||
return
|
||||
|
|
@ -409,11 +438,8 @@ def process_info(self, info_dict):
|
|||
try:
|
||||
srtfn = filename.rsplit('.', 1)[0] + u'.srt'
|
||||
self.report_writesubtitles(srtfn)
|
||||
srtfile = open(encodeFilename(srtfn), 'wb')
|
||||
try:
|
||||
srtfile.write(info_dict['subtitles'].encode('utf-8'))
|
||||
finally:
|
||||
srtfile.close()
|
||||
with io.open(encodeFilename(srtfn), 'w', encoding='utf-8') as srtfile:
|
||||
srtfile.write(info_dict['subtitles'])
|
||||
except (OSError, IOError):
|
||||
self.trouble(u'ERROR: Cannot write subtitles file ' + descfn)
|
||||
return
|
||||
|
|
@ -422,17 +448,8 @@ def process_info(self, info_dict):
|
|||
infofn = filename + u'.info.json'
|
||||
self.report_writeinfojson(infofn)
|
||||
try:
|
||||
json.dump
|
||||
except (NameError,AttributeError):
|
||||
self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
|
||||
return
|
||||
try:
|
||||
infof = open(encodeFilename(infofn), 'wb')
|
||||
try:
|
||||
json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
|
||||
json.dump(json_info_dict, infof)
|
||||
finally:
|
||||
infof.close()
|
||||
json_info_dict = dict((k, v) for k,v in info_dict.items() if not k in ['urlhandle'])
|
||||
write_json_file(json_info_dict, encodeFilename(infofn))
|
||||
except (OSError, IOError):
|
||||
self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
|
||||
return
|
||||
|
|
@ -443,19 +460,19 @@ def process_info(self, info_dict):
|
|||
else:
|
||||
try:
|
||||
success = self._do_download(filename, info_dict)
|
||||
except (OSError, IOError), err:
|
||||
raise UnavailableVideoError
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
except (OSError, IOError) as err:
|
||||
raise UnavailableVideoError()
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
self.trouble(u'ERROR: unable to download video data: %s' % str(err))
|
||||
return
|
||||
except (ContentTooShortError, ), err:
|
||||
except (ContentTooShortError, ) as err:
|
||||
self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
|
||||
return
|
||||
|
||||
if success:
|
||||
try:
|
||||
self.post_process(filename, info_dict)
|
||||
except (PostProcessingError), err:
|
||||
except (PostProcessingError) as err:
|
||||
self.trouble(u'ERROR: postprocessing: %s' % str(err))
|
||||
return
|
||||
|
||||
|
|
@ -471,11 +488,30 @@ def download(self, url_list):
|
|||
if not ie.suitable(url):
|
||||
continue
|
||||
|
||||
# Warn if the _WORKING attribute is False
|
||||
if not ie.working():
|
||||
self.to_stderr(u'WARNING: the program functionality for this site has been marked as broken, '
|
||||
u'and will probably not work. If you want to go on, use the -i option.')
|
||||
|
||||
# Suitable InfoExtractor found
|
||||
suitable_found = True
|
||||
|
||||
# Extract information from URL and process it
|
||||
try:
|
||||
videos = ie.extract(url)
|
||||
except ExtractorError as de: # An error we somewhat expected
|
||||
self.trouble(u'ERROR: ' + compat_str(de), de.format_traceback())
|
||||
break
|
||||
except Exception as e:
|
||||
if self.params.get('ignoreerrors', False):
|
||||
self.trouble(u'ERROR: ' + compat_str(e), tb=compat_str(traceback.format_exc()))
|
||||
break
|
||||
else:
|
||||
raise
|
||||
|
||||
if len(videos or []) > 1 and self.fixed_template():
|
||||
raise SameFileError(self.params['outtmpl'])
|
||||
|
||||
for video in videos or []:
|
||||
video['extractor'] = ie.IE_NAME
|
||||
try:
|
||||
|
|
@ -501,7 +537,7 @@ def post_process(self, filename, ie_info):
|
|||
if info is None:
|
||||
break
|
||||
|
||||
def _download_with_rtmpdump(self, filename, url, player_url):
|
||||
def _download_with_rtmpdump(self, filename, url, player_url, page_url):
|
||||
self.report_destination(filename)
|
||||
tmpfilename = self.temp_name(filename)
|
||||
|
||||
|
|
@ -515,7 +551,11 @@ def _download_with_rtmpdump(self, filename, url, player_url):
|
|||
# Download using rtmpdump. rtmpdump returns exit code 2 when
|
||||
# the connection was interrumpted and resuming appears to be
|
||||
# possible. This is part of rtmpdump's normal usage, AFAIK.
|
||||
basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
|
||||
basic_args = ['rtmpdump', '-q', '-r', url, '-o', tmpfilename]
|
||||
if player_url is not None:
|
||||
basic_args += ['-W', player_url]
|
||||
if page_url is not None:
|
||||
basic_args += ['--pageUrl', page_url]
|
||||
args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]
|
||||
if self.params.get('verbose', False):
|
||||
try:
|
||||
|
|
@ -548,7 +588,6 @@ def _download_with_rtmpdump(self, filename, url, player_url):
|
|||
|
||||
def _do_download(self, filename, info_dict):
|
||||
url = info_dict['url']
|
||||
player_url = info_dict.get('player_url', None)
|
||||
|
||||
# Check file already present
|
||||
if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False):
|
||||
|
|
@ -557,15 +596,20 @@ def _do_download(self, filename, info_dict):
|
|||
|
||||
# Attempt to download using rtmpdump
|
||||
if url.startswith('rtmp'):
|
||||
return self._download_with_rtmpdump(filename, url, player_url)
|
||||
return self._download_with_rtmpdump(filename, url,
|
||||
info_dict.get('player_url', None),
|
||||
info_dict.get('page_url', None))
|
||||
|
||||
tmpfilename = self.temp_name(filename)
|
||||
stream = None
|
||||
|
||||
# Do not include the Accept-Encoding header
|
||||
headers = {'Youtubedl-no-compression': 'True'}
|
||||
basic_request = urllib2.Request(url, None, headers)
|
||||
request = urllib2.Request(url, None, headers)
|
||||
basic_request = compat_urllib_request.Request(url, None, headers)
|
||||
request = compat_urllib_request.Request(url, None, headers)
|
||||
|
||||
if self.params.get('test', False):
|
||||
request.add_header('Range','bytes=0-10240')
|
||||
|
||||
# Establish possible resume length
|
||||
if os.path.isfile(encodeFilename(tmpfilename)):
|
||||
|
|
@ -589,9 +633,9 @@ def _do_download(self, filename, info_dict):
|
|||
try:
|
||||
if count == 0 and 'urlhandle' in info_dict:
|
||||
data = info_dict['urlhandle']
|
||||
data = urllib2.urlopen(request)
|
||||
data = compat_urllib_request.urlopen(request)
|
||||
break
|
||||
except (urllib2.HTTPError, ), err:
|
||||
except (compat_urllib_error.HTTPError, ) as err:
|
||||
if (err.code < 500 or err.code >= 600) and err.code != 416:
|
||||
# Unexpected HTTP error
|
||||
raise
|
||||
|
|
@ -599,15 +643,15 @@ def _do_download(self, filename, info_dict):
|
|||
# Unable to resume (requested range not satisfiable)
|
||||
try:
|
||||
# Open the connection again without the range header
|
||||
data = urllib2.urlopen(basic_request)
|
||||
data = compat_urllib_request.urlopen(basic_request)
|
||||
content_length = data.info()['Content-Length']
|
||||
except (urllib2.HTTPError, ), err:
|
||||
except (compat_urllib_error.HTTPError, ) as err:
|
||||
if err.code < 500 or err.code >= 600:
|
||||
raise
|
||||
else:
|
||||
# Examine the reported length
|
||||
if (content_length is not None and
|
||||
(resume_len - 100 < long(content_length) < resume_len + 100)):
|
||||
(resume_len - 100 < int(content_length) < resume_len + 100)):
|
||||
# The file had already been fully downloaded.
|
||||
# Explanation to the above condition: in issue #175 it was revealed that
|
||||
# YouTube sometimes adds or removes a few bytes from the end of the file,
|
||||
|
|
@ -634,10 +678,10 @@ def _do_download(self, filename, info_dict):
|
|||
|
||||
data_len = data.info().get('Content-length', None)
|
||||
if data_len is not None:
|
||||
data_len = long(data_len) + resume_len
|
||||
data_len = int(data_len) + resume_len
|
||||
data_len_str = self.format_bytes(data_len)
|
||||
byte_counter = 0 + resume_len
|
||||
block_size = 1024
|
||||
block_size = self.params.get('buffersize', 1024)
|
||||
start = time.time()
|
||||
while True:
|
||||
# Download and write
|
||||
|
|
@ -655,14 +699,15 @@ def _do_download(self, filename, info_dict):
|
|||
assert stream is not None
|
||||
filename = self.undo_temp_name(tmpfilename)
|
||||
self.report_destination(filename)
|
||||
except (OSError, IOError), err:
|
||||
except (OSError, IOError) as err:
|
||||
self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
|
||||
return False
|
||||
try:
|
||||
stream.write(data_block)
|
||||
except (IOError, OSError), err:
|
||||
except (IOError, OSError) as err:
|
||||
self.trouble(u'\nERROR: unable to write data: %s' % str(err))
|
||||
return False
|
||||
if not self.params.get('noresizebuffer', False):
|
||||
block_size = self.best_block_size(after - before, len(data_block))
|
||||
|
||||
# Progress message
|
||||
|
|
@ -683,7 +728,7 @@ def _do_download(self, filename, info_dict):
|
|||
stream.close()
|
||||
self.report_finish()
|
||||
if data_len is not None and byte_counter != data_len:
|
||||
raise ContentTooShortError(byte_counter, long(data_len))
|
||||
raise ContentTooShortError(byte_counter, int(data_len))
|
||||
self.try_rename(tmpfilename, filename)
|
||||
|
||||
# Update file modification time
|
||||
|
|
|
|||
1954
youtube_dl/InfoExtractors.py
Normal file → Executable file
1954
youtube_dl/InfoExtractors.py
Normal file → Executable file
File diff suppressed because it is too large
Load diff
|
|
@ -1,12 +1,14 @@
|
|||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from __future__ import absolute_import
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
|
||||
from utils import *
|
||||
from .utils import *
|
||||
|
||||
|
||||
class PostProcessor(object):
|
||||
|
|
@ -60,13 +62,14 @@ def __init__(self, message):
|
|||
self.message = message
|
||||
|
||||
class FFmpegExtractAudioPP(PostProcessor):
|
||||
def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False):
|
||||
def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False, nopostoverwrites=False):
|
||||
PostProcessor.__init__(self, downloader)
|
||||
if preferredcodec is None:
|
||||
preferredcodec = 'best'
|
||||
self._preferredcodec = preferredcodec
|
||||
self._preferredquality = preferredquality
|
||||
self._keepvideo = keepvideo
|
||||
self._nopostoverwrites = nopostoverwrites
|
||||
self._exes = self.detect_executables()
|
||||
|
||||
@staticmethod
|
||||
|
|
@ -84,14 +87,14 @@ def get_audio_codec(self, path):
|
|||
if not self._exes['ffprobe'] and not self._exes['avprobe']: return None
|
||||
try:
|
||||
cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', '--', encodeFilename(path)]
|
||||
handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
|
||||
handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE)
|
||||
output = handle.communicate()[0]
|
||||
if handle.wait() != 0:
|
||||
return None
|
||||
except (IOError, OSError):
|
||||
return None
|
||||
audio_codec = None
|
||||
for line in output.split('\n'):
|
||||
for line in output.decode('ascii', 'ignore').split('\n'):
|
||||
if line.startswith('codec_name='):
|
||||
audio_codec = line.split('=')[1].strip()
|
||||
elif line.strip() == 'codec_type=audio' and audio_codec is not None:
|
||||
|
|
@ -169,8 +172,11 @@ def run(self, information):
|
|||
|
||||
prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
|
||||
new_path = prefix + sep + extension
|
||||
self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path)
|
||||
try:
|
||||
if self._nopostoverwrites and os.path.exists(encodeFilename(new_path)):
|
||||
self._downloader.to_screen(u'[youtube] Post-process file %s exists, skipping' % new_path)
|
||||
else:
|
||||
self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path)
|
||||
self.run_ffmpeg(path, new_path, acodec, more_opts)
|
||||
except:
|
||||
etype,e,tb = sys.exc_info()
|
||||
|
|
|
|||
|
|
@ -2,6 +2,7 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
from __future__ import with_statement
|
||||
from __future__ import absolute_import
|
||||
|
||||
__authors__ = (
|
||||
'Ricardo Garcia Gonzalez',
|
||||
|
|
@ -18,17 +19,13 @@
|
|||
'Ori Avtalion',
|
||||
'shizeeg',
|
||||
'Filippo Valsorda',
|
||||
'Christian Albrecht',
|
||||
'Dave Vasilevsky',
|
||||
'Jaime Marquínez Ferrándiz',
|
||||
)
|
||||
|
||||
__license__ = 'Public Domain'
|
||||
__version__ = '2012.10.09'
|
||||
|
||||
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
|
||||
UPDATE_URL_VERSION = 'https://raw.github.com/rg3/youtube-dl/master/LATEST_VERSION'
|
||||
UPDATE_URL_EXE = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl.exe'
|
||||
|
||||
|
||||
import cookielib
|
||||
import getpass
|
||||
import optparse
|
||||
import os
|
||||
|
|
@ -37,77 +34,15 @@
|
|||
import socket
|
||||
import subprocess
|
||||
import sys
|
||||
import urllib2
|
||||
import warnings
|
||||
import platform
|
||||
|
||||
from utils import *
|
||||
from FileDownloader import *
|
||||
from InfoExtractors import *
|
||||
from PostProcessor import *
|
||||
|
||||
def updateSelf(downloader, filename):
|
||||
''' Update the program file with the latest version from the repository '''
|
||||
# Note: downloader only used for options
|
||||
|
||||
if not os.access(filename, os.W_OK):
|
||||
sys.exit('ERROR: no write permissions on %s' % filename)
|
||||
|
||||
downloader.to_screen(u'Updating to latest version...')
|
||||
|
||||
urlv = urllib2.urlopen(UPDATE_URL_VERSION)
|
||||
newversion = urlv.read().strip()
|
||||
if newversion == __version__:
|
||||
downloader.to_screen(u'youtube-dl is up-to-date (' + __version__ + ')')
|
||||
return
|
||||
urlv.close()
|
||||
|
||||
if hasattr(sys, "frozen"): #py2exe
|
||||
exe = os.path.abspath(filename)
|
||||
directory = os.path.dirname(exe)
|
||||
if not os.access(directory, os.W_OK):
|
||||
sys.exit('ERROR: no write permissions on %s' % directory)
|
||||
|
||||
try:
|
||||
urlh = urllib2.urlopen(UPDATE_URL_EXE)
|
||||
newcontent = urlh.read()
|
||||
urlh.close()
|
||||
with open(exe + '.new', 'wb') as outf:
|
||||
outf.write(newcontent)
|
||||
except (IOError, OSError), err:
|
||||
sys.exit('ERROR: unable to download latest version')
|
||||
|
||||
try:
|
||||
bat = os.path.join(directory, 'youtube-dl-updater.bat')
|
||||
b = open(bat, 'w')
|
||||
|
||||
print >> b, """
|
||||
echo Updating youtube-dl...
|
||||
ping 127.0.0.1 -n 5 -w 1000 > NUL
|
||||
move /Y "%s.new" "%s"
|
||||
del "%s"
|
||||
""" %(exe, exe, bat)
|
||||
|
||||
b.close()
|
||||
|
||||
os.startfile(bat)
|
||||
except (IOError, OSError), err:
|
||||
sys.exit('ERROR: unable to overwrite current version')
|
||||
|
||||
else:
|
||||
try:
|
||||
urlh = urllib2.urlopen(UPDATE_URL)
|
||||
newcontent = urlh.read()
|
||||
urlh.close()
|
||||
except (IOError, OSError), err:
|
||||
sys.exit('ERROR: unable to download latest version')
|
||||
|
||||
try:
|
||||
with open(filename, 'wb') as outf:
|
||||
outf.write(newcontent)
|
||||
except (IOError, OSError), err:
|
||||
sys.exit('ERROR: unable to overwrite current version')
|
||||
|
||||
downloader.to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.')
|
||||
from .utils import *
|
||||
from .update import update_self
|
||||
from .version import __version__
|
||||
from .FileDownloader import *
|
||||
from .InfoExtractors import gen_extractors
|
||||
from .PostProcessor import *
|
||||
|
||||
def parseOpts():
|
||||
def _readOptions(filename_bytes):
|
||||
|
|
@ -128,9 +63,12 @@ def _format_option_string(option):
|
|||
|
||||
opts = []
|
||||
|
||||
if option._short_opts: opts.append(option._short_opts[0])
|
||||
if option._long_opts: opts.append(option._long_opts[0])
|
||||
if len(opts) > 1: opts.insert(1, ', ')
|
||||
if option._short_opts:
|
||||
opts.append(option._short_opts[0])
|
||||
if option._long_opts:
|
||||
opts.append(option._long_opts[0])
|
||||
if len(opts) > 1:
|
||||
opts.insert(1, ', ')
|
||||
|
||||
if option.takes_value(): opts.append(' %s' % option.metavar)
|
||||
|
||||
|
|
@ -189,6 +127,11 @@ def _find_term_columns():
|
|||
dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
|
||||
general.add_option('-R', '--retries',
|
||||
dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10)
|
||||
general.add_option('--buffer-size',
|
||||
dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16k) (default is %default)', default="1024")
|
||||
general.add_option('--no-resize-buffer',
|
||||
action='store_true', dest='noresizebuffer',
|
||||
help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False)
|
||||
general.add_option('--dump-user-agent',
|
||||
action='store_true', dest='dump_user_agent',
|
||||
help='display the current browser identification', default=False)
|
||||
|
|
@ -197,6 +140,7 @@ def _find_term_columns():
|
|||
general.add_option('--list-extractors',
|
||||
action='store_true', dest='list_extractors',
|
||||
help='List all supported extractors and the URLs they would handle', default=False)
|
||||
general.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
|
||||
|
||||
selection.add_option('--playlist-start',
|
||||
dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is %default)', default=1)
|
||||
|
|
@ -268,12 +212,15 @@ def _find_term_columns():
|
|||
filesystem.add_option('--id',
|
||||
action='store_true', dest='useid', help='use video ID in file name', default=False)
|
||||
filesystem.add_option('-l', '--literal',
|
||||
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
|
||||
action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False)
|
||||
filesystem.add_option('-A', '--auto-number',
|
||||
action='store_true', dest='autonumber',
|
||||
help='number downloaded files starting from 00000', default=False)
|
||||
filesystem.add_option('-o', '--output',
|
||||
dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout.')
|
||||
dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout. Can also be used to download to a different directory, for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .')
|
||||
filesystem.add_option('--restrict-filenames',
|
||||
action='store_true', dest='restrictfilenames',
|
||||
help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
|
||||
filesystem.add_option('-a', '--batch-file',
|
||||
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
|
||||
filesystem.add_option('-w', '--no-overwrites',
|
||||
|
|
@ -306,6 +253,8 @@ def _find_term_columns():
|
|||
help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)')
|
||||
postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
|
||||
help='keeps the video file on disk after the post-processing; the video is erased by default')
|
||||
postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
|
||||
help='do not overwrite post-processed files; the post-processed files are overwritten by default')
|
||||
|
||||
|
||||
parser.add_option_group(general)
|
||||
|
|
@ -326,59 +275,18 @@ def _find_term_columns():
|
|||
|
||||
return parser, opts, args
|
||||
|
||||
def gen_extractors():
|
||||
""" Return a list of an instance of every supported extractor.
|
||||
The order does matter; the first extractor matched is the one handling the URL.
|
||||
"""
|
||||
return [
|
||||
YoutubePlaylistIE(),
|
||||
YoutubeChannelIE(),
|
||||
YoutubeUserIE(),
|
||||
YoutubeSearchIE(),
|
||||
YoutubeIE(),
|
||||
MetacafeIE(),
|
||||
DailymotionIE(),
|
||||
GoogleIE(),
|
||||
GoogleSearchIE(),
|
||||
PhotobucketIE(),
|
||||
YahooIE(),
|
||||
YahooSearchIE(),
|
||||
DepositFilesIE(),
|
||||
FacebookIE(),
|
||||
BlipTVUserIE(),
|
||||
BlipTVIE(),
|
||||
VimeoIE(),
|
||||
MyVideoIE(),
|
||||
ComedyCentralIE(),
|
||||
EscapistIE(),
|
||||
CollegeHumorIE(),
|
||||
XVideosIE(),
|
||||
SoundcloudIE(),
|
||||
InfoQIE(),
|
||||
MixcloudIE(),
|
||||
StanfordOpenClassroomIE(),
|
||||
MTVIE(),
|
||||
YoukuIE(),
|
||||
XNXXIE(),
|
||||
GooglePlusIE(),
|
||||
PornotubeIE(),
|
||||
YouPornIE(),
|
||||
YouJizzIE(),
|
||||
GenericIE()
|
||||
]
|
||||
|
||||
def _real_main():
|
||||
parser, opts, args = parseOpts()
|
||||
|
||||
# Open appropriate CookieJar
|
||||
if opts.cookiefile is None:
|
||||
jar = cookielib.CookieJar()
|
||||
jar = compat_cookiejar.CookieJar()
|
||||
else:
|
||||
try:
|
||||
jar = cookielib.MozillaCookieJar(opts.cookiefile)
|
||||
jar = compat_cookiejar.MozillaCookieJar(opts.cookiefile)
|
||||
if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
|
||||
jar.load()
|
||||
except (IOError, OSError), err:
|
||||
except (IOError, OSError) as err:
|
||||
sys.exit(u'ERROR: unable to open cookie file')
|
||||
# Set user agent
|
||||
if opts.user_agent is not None:
|
||||
|
|
@ -386,7 +294,7 @@ def _real_main():
|
|||
|
||||
# Dump user agent
|
||||
if opts.dump_user_agent:
|
||||
print std_headers['User-Agent']
|
||||
print(std_headers['User-Agent'])
|
||||
sys.exit(0)
|
||||
|
||||
# Batch file verification
|
||||
|
|
@ -403,22 +311,22 @@ def _real_main():
|
|||
except IOError:
|
||||
sys.exit(u'ERROR: batch file could not be read')
|
||||
all_urls = batchurls + args
|
||||
all_urls = map(lambda url: url.strip(), all_urls)
|
||||
all_urls = [url.strip() for url in all_urls]
|
||||
|
||||
# General configuration
|
||||
cookie_processor = urllib2.HTTPCookieProcessor(jar)
|
||||
proxy_handler = urllib2.ProxyHandler()
|
||||
opener = urllib2.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
|
||||
urllib2.install_opener(opener)
|
||||
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
|
||||
proxy_handler = compat_urllib_request.ProxyHandler()
|
||||
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
|
||||
compat_urllib_request.install_opener(opener)
|
||||
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
|
||||
|
||||
extractors = gen_extractors()
|
||||
|
||||
if opts.list_extractors:
|
||||
for ie in extractors:
|
||||
print(ie.IE_NAME)
|
||||
matchedUrls = filter(lambda url: ie.suitable(url), all_urls)
|
||||
all_urls = filter(lambda url: url not in matchedUrls, all_urls)
|
||||
print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
|
||||
matchedUrls = [url for url in all_urls if ie.suitable(url)]
|
||||
all_urls = [url for url in all_urls if url not in matchedUrls]
|
||||
for mu in matchedUrls:
|
||||
print(u' ' + mu)
|
||||
sys.exit(0)
|
||||
|
|
@ -428,14 +336,10 @@ def _real_main():
|
|||
parser.error(u'using .netrc conflicts with giving username/password')
|
||||
if opts.password is not None and opts.username is None:
|
||||
parser.error(u'account username missing')
|
||||
if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber or opts.useid):
|
||||
parser.error(u'using output template conflicts with using title, literal title, video ID or auto number')
|
||||
if opts.usetitle and opts.useliteral:
|
||||
parser.error(u'using title conflicts with using literal title')
|
||||
if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
|
||||
parser.error(u'using output template conflicts with using title, video ID or auto number')
|
||||
if opts.usetitle and opts.useid:
|
||||
parser.error(u'using title conflicts with using video ID')
|
||||
if opts.useliteral and opts.useid:
|
||||
parser.error(u'using literal title conflicts with using video ID')
|
||||
if opts.username is not None and opts.password is None:
|
||||
opts.password = getpass.getpass(u'Type account password and press return:')
|
||||
if opts.ratelimit is not None:
|
||||
|
|
@ -445,20 +349,25 @@ def _real_main():
|
|||
opts.ratelimit = numeric_limit
|
||||
if opts.retries is not None:
|
||||
try:
|
||||
opts.retries = long(opts.retries)
|
||||
except (TypeError, ValueError), err:
|
||||
opts.retries = int(opts.retries)
|
||||
except (TypeError, ValueError) as err:
|
||||
parser.error(u'invalid retry count specified')
|
||||
if opts.buffersize is not None:
|
||||
numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
|
||||
if numeric_buffersize is None:
|
||||
parser.error(u'invalid buffer size specified')
|
||||
opts.buffersize = numeric_buffersize
|
||||
try:
|
||||
opts.playliststart = int(opts.playliststart)
|
||||
if opts.playliststart <= 0:
|
||||
raise ValueError(u'Playlist start must be positive')
|
||||
except (TypeError, ValueError), err:
|
||||
except (TypeError, ValueError) as err:
|
||||
parser.error(u'invalid playlist start number specified')
|
||||
try:
|
||||
opts.playlistend = int(opts.playlistend)
|
||||
if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
|
||||
raise ValueError(u'Playlist end must be greater than playlist start')
|
||||
except (TypeError, ValueError), err:
|
||||
except (TypeError, ValueError) as err:
|
||||
parser.error(u'invalid playlist end number specified')
|
||||
if opts.extractaudio:
|
||||
if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']:
|
||||
|
|
@ -468,6 +377,18 @@ def _real_main():
|
|||
if not opts.audioquality.isdigit():
|
||||
parser.error(u'invalid audio quality specified')
|
||||
|
||||
if sys.version_info < (3,):
|
||||
# In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
|
||||
if opts.outtmpl is not None:
|
||||
opts.outtmpl = opts.outtmpl.decode(preferredencoding())
|
||||
outtmpl =((opts.outtmpl is not None and opts.outtmpl)
|
||||
or (opts.format == '-1' and opts.usetitle and u'%(title)s-%(id)s-%(format)s.%(ext)s')
|
||||
or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
|
||||
or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
|
||||
or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
|
||||
or (opts.useid and u'%(id)s.%(ext)s')
|
||||
or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
|
||||
or u'%(id)s.%(ext)s')
|
||||
# File downloader
|
||||
fd = FileDownloader({
|
||||
'usenetrc': opts.usenetrc,
|
||||
|
|
@ -485,21 +406,14 @@ def _real_main():
|
|||
'format': opts.format,
|
||||
'format_limit': opts.format_limit,
|
||||
'listformats': opts.listformats,
|
||||
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
|
||||
or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
|
||||
or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
|
||||
or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
|
||||
or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s')
|
||||
or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
|
||||
or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
|
||||
or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
|
||||
or (opts.useid and u'%(id)s.%(ext)s')
|
||||
or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
|
||||
or u'%(id)s.%(ext)s'),
|
||||
'outtmpl': outtmpl,
|
||||
'restrictfilenames': opts.restrictfilenames,
|
||||
'ignoreerrors': opts.ignoreerrors,
|
||||
'ratelimit': opts.ratelimit,
|
||||
'nooverwrites': opts.nooverwrites,
|
||||
'retries': opts.retries,
|
||||
'buffersize': opts.buffersize,
|
||||
'noresizebuffer': opts.noresizebuffer,
|
||||
'continuedl': opts.continue_dl,
|
||||
'noprogress': opts.noprogress,
|
||||
'playliststart': opts.playliststart,
|
||||
|
|
@ -517,9 +431,21 @@ def _real_main():
|
|||
'max_downloads': opts.max_downloads,
|
||||
'prefer_free_formats': opts.prefer_free_formats,
|
||||
'verbose': opts.verbose,
|
||||
'test': opts.test,
|
||||
})
|
||||
|
||||
if opts.verbose:
|
||||
fd.to_screen(u'[debug] youtube-dl version ' + __version__)
|
||||
try:
|
||||
sp = subprocess.Popen(['git', 'rev-parse', '--short', 'HEAD'], stdout=subprocess.PIPE, stderr=subprocess.PIPE,
|
||||
cwd=os.path.dirname(os.path.abspath(__file__)))
|
||||
out, err = sp.communicate()
|
||||
out = out.decode().strip()
|
||||
if re.match('[0-9a-f]+', out):
|
||||
fd.to_screen(u'[debug] Git HEAD: ' + out)
|
||||
except:
|
||||
pass
|
||||
fd.to_screen(u'[debug] Python version %s - %s' %(platform.python_version(), platform.platform()))
|
||||
fd.to_screen(u'[debug] Proxy map: ' + str(proxy_handler.proxies))
|
||||
|
||||
for extractor in extractors:
|
||||
|
|
@ -527,11 +453,11 @@ def _real_main():
|
|||
|
||||
# PostProcessors
|
||||
if opts.extractaudio:
|
||||
fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo))
|
||||
fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo, nopostoverwrites=opts.nopostoverwrites))
|
||||
|
||||
# Update version
|
||||
if opts.update_self:
|
||||
updateSelf(fd, sys.argv[0])
|
||||
update_self(fd.to_screen, opts.verbose, sys.argv[0])
|
||||
|
||||
# Maybe do nothing
|
||||
if len(all_urls) < 1:
|
||||
|
|
@ -550,7 +476,7 @@ def _real_main():
|
|||
if opts.cookiefile is not None:
|
||||
try:
|
||||
jar.save()
|
||||
except (IOError, OSError), err:
|
||||
except (IOError, OSError) as err:
|
||||
sys.exit(u'ERROR: unable to save cookie jar')
|
||||
|
||||
sys.exit(retcode)
|
||||
|
|
|
|||
|
|
@ -1,7 +1,17 @@
|
|||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import __init__
|
||||
# Execute with
|
||||
# $ python youtube_dl/__main__.py (2.6+)
|
||||
# $ python -m youtube_dl (2.7+)
|
||||
|
||||
import sys
|
||||
|
||||
if __package__ is None and not hasattr(sys, "frozen"):
|
||||
# direct call of __main__.py
|
||||
import os.path
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
import youtube_dl
|
||||
|
||||
if __name__ == '__main__':
|
||||
__init__.main()
|
||||
youtube_dl.main()
|
||||
|
|
|
|||
160
youtube_dl/update.py
Normal file
160
youtube_dl/update.py
Normal file
|
|
@ -0,0 +1,160 @@
|
|||
import json
|
||||
import traceback
|
||||
import hashlib
|
||||
from zipimport import zipimporter
|
||||
|
||||
from .utils import *
|
||||
from .version import __version__
|
||||
|
||||
def rsa_verify(message, signature, key):
|
||||
from struct import pack
|
||||
from hashlib import sha256
|
||||
from sys import version_info
|
||||
def b(x):
|
||||
if version_info[0] == 2: return x
|
||||
else: return x.encode('latin1')
|
||||
assert(type(message) == type(b('')))
|
||||
block_size = 0
|
||||
n = key[0]
|
||||
while n:
|
||||
block_size += 1
|
||||
n >>= 8
|
||||
signature = pow(int(signature, 16), key[1], key[0])
|
||||
raw_bytes = []
|
||||
while signature:
|
||||
raw_bytes.insert(0, pack("B", signature & 0xFF))
|
||||
signature >>= 8
|
||||
signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
|
||||
if signature[0:2] != b('\x00\x01'): return False
|
||||
signature = signature[2:]
|
||||
if not b('\x00') in signature: return False
|
||||
signature = signature[signature.index(b('\x00'))+1:]
|
||||
if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
|
||||
signature = signature[19:]
|
||||
if signature != sha256(message).digest(): return False
|
||||
return True
|
||||
|
||||
def update_self(to_screen, verbose, filename):
|
||||
"""Update the program file with the latest version from the repository"""
|
||||
|
||||
UPDATE_URL = "http://rg3.github.com/youtube-dl/update/"
|
||||
VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
|
||||
JSON_URL = UPDATE_URL + 'versions.json'
|
||||
UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
|
||||
|
||||
|
||||
if not isinstance(globals().get('__loader__'), zipimporter) and not hasattr(sys, "frozen"):
|
||||
to_screen(u'It looks like you installed youtube-dl with pip, setup.py or a tarball. Please use that to update.')
|
||||
return
|
||||
|
||||
# Check if there is a new version
|
||||
try:
|
||||
newversion = compat_urllib_request.urlopen(VERSION_URL).read().decode('utf-8').strip()
|
||||
except:
|
||||
if verbose: to_screen(compat_str(traceback.format_exc()))
|
||||
to_screen(u'ERROR: can\'t find the current version. Please try again later.')
|
||||
return
|
||||
if newversion == __version__:
|
||||
to_screen(u'youtube-dl is up-to-date (' + __version__ + ')')
|
||||
return
|
||||
|
||||
# Download and check versions info
|
||||
try:
|
||||
versions_info = compat_urllib_request.urlopen(JSON_URL).read().decode('utf-8')
|
||||
versions_info = json.loads(versions_info)
|
||||
except:
|
||||
if verbose: to_screen(compat_str(traceback.format_exc()))
|
||||
to_screen(u'ERROR: can\'t obtain versions info. Please try again later.')
|
||||
return
|
||||
if not 'signature' in versions_info:
|
||||
to_screen(u'ERROR: the versions file is not signed or corrupted. Aborting.')
|
||||
return
|
||||
signature = versions_info['signature']
|
||||
del versions_info['signature']
|
||||
if not rsa_verify(json.dumps(versions_info, sort_keys=True).encode('utf-8'), signature, UPDATES_RSA_KEY):
|
||||
to_screen(u'ERROR: the versions file signature is invalid. Aborting.')
|
||||
return
|
||||
|
||||
to_screen(u'Updating to version ' + versions_info['latest'] + '...')
|
||||
version = versions_info['versions'][versions_info['latest']]
|
||||
if version.get('notes'):
|
||||
to_screen(u'PLEASE NOTE:')
|
||||
for note in version['notes']:
|
||||
to_screen(note)
|
||||
|
||||
if not os.access(filename, os.W_OK):
|
||||
to_screen(u'ERROR: no write permissions on %s' % filename)
|
||||
return
|
||||
|
||||
# Py2EXE
|
||||
if hasattr(sys, "frozen"):
|
||||
exe = os.path.abspath(filename)
|
||||
directory = os.path.dirname(exe)
|
||||
if not os.access(directory, os.W_OK):
|
||||
to_screen(u'ERROR: no write permissions on %s' % directory)
|
||||
return
|
||||
|
||||
try:
|
||||
urlh = compat_urllib_request.urlopen(version['exe'][0])
|
||||
newcontent = urlh.read()
|
||||
urlh.close()
|
||||
except (IOError, OSError) as err:
|
||||
if verbose: to_screen(compat_str(traceback.format_exc()))
|
||||
to_screen(u'ERROR: unable to download latest version')
|
||||
return
|
||||
|
||||
newcontent_hash = hashlib.sha256(newcontent).hexdigest()
|
||||
if newcontent_hash != version['exe'][1]:
|
||||
to_screen(u'ERROR: the downloaded file hash does not match. Aborting.')
|
||||
return
|
||||
|
||||
try:
|
||||
with open(exe + '.new', 'wb') as outf:
|
||||
outf.write(newcontent)
|
||||
except (IOError, OSError) as err:
|
||||
if verbose: to_screen(compat_str(traceback.format_exc()))
|
||||
to_screen(u'ERROR: unable to write the new version')
|
||||
return
|
||||
|
||||
try:
|
||||
bat = os.path.join(directory, 'youtube-dl-updater.bat')
|
||||
b = open(bat, 'w')
|
||||
b.write("""
|
||||
echo Updating youtube-dl...
|
||||
ping 127.0.0.1 -n 5 -w 1000 > NUL
|
||||
move /Y "%s.new" "%s"
|
||||
del "%s"
|
||||
\n""" %(exe, exe, bat))
|
||||
b.close()
|
||||
|
||||
os.startfile(bat)
|
||||
except (IOError, OSError) as err:
|
||||
if verbose: to_screen(compat_str(traceback.format_exc()))
|
||||
to_screen(u'ERROR: unable to overwrite current version')
|
||||
return
|
||||
|
||||
# Zip unix package
|
||||
elif isinstance(globals().get('__loader__'), zipimporter):
|
||||
try:
|
||||
urlh = compat_urllib_request.urlopen(version['bin'][0])
|
||||
newcontent = urlh.read()
|
||||
urlh.close()
|
||||
except (IOError, OSError) as err:
|
||||
if verbose: to_screen(compat_str(traceback.format_exc()))
|
||||
to_screen(u'ERROR: unable to download latest version')
|
||||
return
|
||||
|
||||
newcontent_hash = hashlib.sha256(newcontent).hexdigest()
|
||||
if newcontent_hash != version['bin'][1]:
|
||||
to_screen(u'ERROR: the downloaded file hash does not match. Aborting.')
|
||||
return
|
||||
|
||||
try:
|
||||
with open(filename, 'wb') as outf:
|
||||
outf.write(newcontent)
|
||||
except (IOError, OSError) as err:
|
||||
if verbose: to_screen(compat_str(traceback.format_exc()))
|
||||
to_screen(u'ERROR: unable to overwrite current version')
|
||||
return
|
||||
|
||||
to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.')
|
||||
|
|
@ -2,21 +2,151 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import gzip
|
||||
import htmlentitydefs
|
||||
import HTMLParser
|
||||
import io
|
||||
import json
|
||||
import locale
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
import traceback
|
||||
import zlib
|
||||
import urllib2
|
||||
import email.utils
|
||||
import json
|
||||
|
||||
try:
|
||||
import cStringIO as StringIO
|
||||
import urllib.request as compat_urllib_request
|
||||
except ImportError: # Python 2
|
||||
import urllib2 as compat_urllib_request
|
||||
|
||||
try:
|
||||
import urllib.error as compat_urllib_error
|
||||
except ImportError: # Python 2
|
||||
import urllib2 as compat_urllib_error
|
||||
|
||||
try:
|
||||
import urllib.parse as compat_urllib_parse
|
||||
except ImportError: # Python 2
|
||||
import urllib as compat_urllib_parse
|
||||
|
||||
try:
|
||||
from urllib.parse import urlparse as compat_urllib_parse_urlparse
|
||||
except ImportError: # Python 2
|
||||
from urlparse import urlparse as compat_urllib_parse_urlparse
|
||||
|
||||
try:
|
||||
import http.cookiejar as compat_cookiejar
|
||||
except ImportError: # Python 2
|
||||
import cookielib as compat_cookiejar
|
||||
|
||||
try:
|
||||
import html.entities as compat_html_entities
|
||||
except ImportError: # Python 2
|
||||
import htmlentitydefs as compat_html_entities
|
||||
|
||||
try:
|
||||
import html.parser as compat_html_parser
|
||||
except ImportError: # Python 2
|
||||
import HTMLParser as compat_html_parser
|
||||
|
||||
try:
|
||||
import http.client as compat_http_client
|
||||
except ImportError: # Python 2
|
||||
import httplib as compat_http_client
|
||||
|
||||
try:
|
||||
from subprocess import DEVNULL
|
||||
compat_subprocess_get_DEVNULL = lambda: DEVNULL
|
||||
except ImportError:
|
||||
import StringIO
|
||||
compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
|
||||
|
||||
try:
|
||||
from urllib.parse import parse_qs as compat_parse_qs
|
||||
except ImportError: # Python 2
|
||||
# HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
|
||||
# Python 2's version is apparently totally broken
|
||||
def _unquote(string, encoding='utf-8', errors='replace'):
|
||||
if string == '':
|
||||
return string
|
||||
res = string.split('%')
|
||||
if len(res) == 1:
|
||||
return string
|
||||
if encoding is None:
|
||||
encoding = 'utf-8'
|
||||
if errors is None:
|
||||
errors = 'replace'
|
||||
# pct_sequence: contiguous sequence of percent-encoded bytes, decoded
|
||||
pct_sequence = b''
|
||||
string = res[0]
|
||||
for item in res[1:]:
|
||||
try:
|
||||
if not item:
|
||||
raise ValueError
|
||||
pct_sequence += item[:2].decode('hex')
|
||||
rest = item[2:]
|
||||
if not rest:
|
||||
# This segment was just a single percent-encoded character.
|
||||
# May be part of a sequence of code units, so delay decoding.
|
||||
# (Stored in pct_sequence).
|
||||
continue
|
||||
except ValueError:
|
||||
rest = '%' + item
|
||||
# Encountered non-percent-encoded characters. Flush the current
|
||||
# pct_sequence.
|
||||
string += pct_sequence.decode(encoding, errors) + rest
|
||||
pct_sequence = b''
|
||||
if pct_sequence:
|
||||
# Flush the final pct_sequence
|
||||
string += pct_sequence.decode(encoding, errors)
|
||||
return string
|
||||
|
||||
def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
|
||||
encoding='utf-8', errors='replace'):
|
||||
qs, _coerce_result = qs, unicode
|
||||
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
|
||||
r = []
|
||||
for name_value in pairs:
|
||||
if not name_value and not strict_parsing:
|
||||
continue
|
||||
nv = name_value.split('=', 1)
|
||||
if len(nv) != 2:
|
||||
if strict_parsing:
|
||||
raise ValueError("bad query field: %r" % (name_value,))
|
||||
# Handle case of a control-name with no equal sign
|
||||
if keep_blank_values:
|
||||
nv.append('')
|
||||
else:
|
||||
continue
|
||||
if len(nv[1]) or keep_blank_values:
|
||||
name = nv[0].replace('+', ' ')
|
||||
name = _unquote(name, encoding=encoding, errors=errors)
|
||||
name = _coerce_result(name)
|
||||
value = nv[1].replace('+', ' ')
|
||||
value = _unquote(value, encoding=encoding, errors=errors)
|
||||
value = _coerce_result(value)
|
||||
r.append((name, value))
|
||||
return r
|
||||
|
||||
def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
|
||||
encoding='utf-8', errors='replace'):
|
||||
parsed_result = {}
|
||||
pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
|
||||
encoding=encoding, errors=errors)
|
||||
for name, value in pairs:
|
||||
if name in parsed_result:
|
||||
parsed_result[name].append(value)
|
||||
else:
|
||||
parsed_result[name] = [value]
|
||||
return parsed_result
|
||||
|
||||
try:
|
||||
compat_str = unicode # Python 2
|
||||
except NameError:
|
||||
compat_str = str
|
||||
|
||||
try:
|
||||
compat_chr = unichr # Python 2
|
||||
except NameError:
|
||||
compat_chr = chr
|
||||
|
||||
std_headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
|
||||
|
|
@ -32,19 +162,35 @@ def preferredencoding():
|
|||
Returns the best encoding scheme for the system, based on
|
||||
locale.getpreferredencoding() and some further tweaks.
|
||||
"""
|
||||
def yield_preferredencoding():
|
||||
try:
|
||||
pref = locale.getpreferredencoding()
|
||||
u'TEST'.encode(pref)
|
||||
except:
|
||||
pref = 'UTF-8'
|
||||
while True:
|
||||
yield pref
|
||||
return yield_preferredencoding().next()
|
||||
|
||||
return pref
|
||||
|
||||
if sys.version_info < (3,0):
|
||||
def compat_print(s):
|
||||
print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
|
||||
else:
|
||||
def compat_print(s):
|
||||
assert type(s) == type(u'')
|
||||
print(s)
|
||||
|
||||
# In Python 2.x, json.dump expects a bytestream.
|
||||
# In Python 3.x, it writes to a character stream
|
||||
if sys.version_info < (3,0):
|
||||
def write_json_file(obj, fn):
|
||||
with open(fn, 'wb') as f:
|
||||
json.dump(obj, f)
|
||||
else:
|
||||
def write_json_file(obj, fn):
|
||||
with open(fn, 'w', encoding='utf-8') as f:
|
||||
json.dump(obj, f)
|
||||
|
||||
def htmlentity_transform(matchobj):
|
||||
"""Transforms an HTML entity to a Unicode character.
|
||||
"""Transforms an HTML entity to a character.
|
||||
|
||||
This function receives a match object and is intended to be used with
|
||||
the re.sub() function.
|
||||
|
|
@ -52,11 +198,10 @@ def htmlentity_transform(matchobj):
|
|||
entity = matchobj.group(1)
|
||||
|
||||
# Known non-numeric HTML entity
|
||||
if entity in htmlentitydefs.name2codepoint:
|
||||
return unichr(htmlentitydefs.name2codepoint[entity])
|
||||
if entity in compat_html_entities.name2codepoint:
|
||||
return compat_chr(compat_html_entities.name2codepoint[entity])
|
||||
|
||||
# Unicode character
|
||||
mobj = re.match(ur'(?u)#(x?\d+)', entity)
|
||||
mobj = re.match(u'(?u)#(x?\\d+)', entity)
|
||||
if mobj is not None:
|
||||
numstr = mobj.group(1)
|
||||
if numstr.startswith(u'x'):
|
||||
|
|
@ -64,28 +209,28 @@ def htmlentity_transform(matchobj):
|
|||
numstr = u'0%s' % numstr
|
||||
else:
|
||||
base = 10
|
||||
return unichr(long(numstr, base))
|
||||
return compat_chr(int(numstr, base))
|
||||
|
||||
# Unknown entity in name, return its literal representation
|
||||
return (u'&%s;' % entity)
|
||||
|
||||
HTMLParser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
|
||||
class IDParser(HTMLParser.HTMLParser):
|
||||
"""Modified HTMLParser that isolates a tag with the specified id"""
|
||||
def __init__(self, id):
|
||||
self.id = id
|
||||
compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
|
||||
class AttrParser(compat_html_parser.HTMLParser):
|
||||
"""Modified HTMLParser that isolates a tag with the specified attribute"""
|
||||
def __init__(self, attribute, value):
|
||||
self.attribute = attribute
|
||||
self.value = value
|
||||
self.result = None
|
||||
self.started = False
|
||||
self.depth = {}
|
||||
self.html = None
|
||||
self.watch_startpos = False
|
||||
self.error_count = 0
|
||||
HTMLParser.HTMLParser.__init__(self)
|
||||
compat_html_parser.HTMLParser.__init__(self)
|
||||
|
||||
def error(self, message):
|
||||
#print >> sys.stderr, self.getpos()
|
||||
if self.error_count > 10 or self.started:
|
||||
raise HTMLParser.HTMLParseError(message, self.getpos())
|
||||
raise compat_html_parser.HTMLParseError(message, self.getpos())
|
||||
self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
|
||||
self.error_count += 1
|
||||
self.goahead(1)
|
||||
|
|
@ -99,7 +244,7 @@ def handle_starttag(self, tag, attrs):
|
|||
attrs = dict(attrs)
|
||||
if self.started:
|
||||
self.find_startpos(None)
|
||||
if 'id' in attrs and attrs['id'] == self.id:
|
||||
if self.attribute in attrs and attrs[self.attribute] == self.value:
|
||||
self.result = [tag]
|
||||
self.started = True
|
||||
self.watch_startpos = True
|
||||
|
|
@ -124,8 +269,10 @@ def find_startpos(self, x):
|
|||
handle_decl = handle_pi = unknown_decl = find_startpos
|
||||
|
||||
def get_result(self):
|
||||
if self.result == None: return None
|
||||
if len(self.result) != 3: return None
|
||||
if self.result is None:
|
||||
return None
|
||||
if len(self.result) != 3:
|
||||
return None
|
||||
lines = self.html.split('\n')
|
||||
lines = lines[self.result[1][0]-1:self.result[2][0]]
|
||||
lines[0] = lines[0][self.result[1][1]:]
|
||||
|
|
@ -135,11 +282,15 @@ def get_result(self):
|
|||
return '\n'.join(lines).strip()
|
||||
|
||||
def get_element_by_id(id, html):
|
||||
"""Return the content of the tag with the specified id in the passed HTML document"""
|
||||
parser = IDParser(id)
|
||||
"""Return the content of the tag with the specified ID in the passed HTML document"""
|
||||
return get_element_by_attribute("id", id, html)
|
||||
|
||||
def get_element_by_attribute(attribute, value, html):
|
||||
"""Return the content of the tag with the specified attribute in the passed HTML document"""
|
||||
parser = AttrParser(attribute, value)
|
||||
try:
|
||||
parser.loads(html)
|
||||
except HTMLParser.HTMLParseError:
|
||||
except compat_html_parser.HTMLParseError:
|
||||
pass
|
||||
return parser.get_result()
|
||||
|
||||
|
|
@ -148,7 +299,8 @@ def clean_html(html):
|
|||
"""Clean an HTML snippet into a readable string"""
|
||||
# Newline vs <br />
|
||||
html = html.replace('\n', ' ')
|
||||
html = re.sub('\s*<\s*br\s*/?\s*>\s*', '\n', html)
|
||||
html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
|
||||
html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
|
||||
# Strip html tags
|
||||
html = re.sub('<.*?>', '', html)
|
||||
# Replace html entities
|
||||
|
|
@ -174,9 +326,9 @@ def sanitize_open(filename, open_mode):
|
|||
return (sys.stdout, filename)
|
||||
stream = open(encodeFilename(filename), open_mode)
|
||||
return (stream, filename)
|
||||
except (IOError, OSError), err:
|
||||
except (IOError, OSError) as err:
|
||||
# In case of error, try to remove win32 forbidden chars
|
||||
filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
|
||||
filename = re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', filename)
|
||||
|
||||
# An exception here should be caught in the caller
|
||||
stream = open(encodeFilename(filename), open_mode)
|
||||
|
|
@ -191,23 +343,37 @@ def timeconvert(timestr):
|
|||
timestamp = email.utils.mktime_tz(timetuple)
|
||||
return timestamp
|
||||
|
||||
def sanitize_filename(s):
|
||||
"""Sanitizes a string so it could be used as part of a filename."""
|
||||
def sanitize_filename(s, restricted=False, is_id=False):
|
||||
"""Sanitizes a string so it could be used as part of a filename.
|
||||
If restricted is set, use a stricter subset of allowed characters.
|
||||
Set is_id if this is not an arbitrary string, but an ID that should be kept if possible
|
||||
"""
|
||||
def replace_insane(char):
|
||||
if char == '?' or ord(char) < 32 or ord(char) == 127:
|
||||
return ''
|
||||
elif char == '"':
|
||||
return '\''
|
||||
return '' if restricted else '\''
|
||||
elif char == ':':
|
||||
return ' -'
|
||||
return '_-' if restricted else ' -'
|
||||
elif char in '\\/|*<>':
|
||||
return '-'
|
||||
return '_'
|
||||
if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()):
|
||||
return '_'
|
||||
if restricted and ord(char) > 127:
|
||||
return '_'
|
||||
return char
|
||||
|
||||
result = u''.join(map(replace_insane, s))
|
||||
while '--' in result:
|
||||
result = result.replace('--', '-')
|
||||
return result.strip('-')
|
||||
if not is_id:
|
||||
while '__' in result:
|
||||
result = result.replace('__', '_')
|
||||
result = result.strip('_')
|
||||
# Common case of "Foreign band name - English song title"
|
||||
if restricted and result.startswith('-_'):
|
||||
result = result[2:]
|
||||
if not result:
|
||||
result = '_'
|
||||
return result
|
||||
|
||||
def orderedSet(iterable):
|
||||
""" Remove all duplicates from the input iterable """
|
||||
|
|
@ -219,20 +385,24 @@ def orderedSet(iterable):
|
|||
|
||||
def unescapeHTML(s):
|
||||
"""
|
||||
@param s a string (of type unicode)
|
||||
@param s a string
|
||||
"""
|
||||
assert type(s) == type(u'')
|
||||
|
||||
result = re.sub(ur'(?u)&(.+?);', htmlentity_transform, s)
|
||||
result = re.sub(u'(?u)&(.+?);', htmlentity_transform, s)
|
||||
return result
|
||||
|
||||
def encodeFilename(s):
|
||||
"""
|
||||
@param s The name of the file (of type unicode)
|
||||
@param s The name of the file
|
||||
"""
|
||||
|
||||
assert type(s) == type(u'')
|
||||
|
||||
# Python 3 has a Unicode API
|
||||
if sys.version_info >= (3, 0):
|
||||
return s
|
||||
|
||||
if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
|
||||
# Pass u'' directly to use Unicode APIs on Windows 2000 and up
|
||||
# (Detecting Windows NT 4 is tricky because 'major >= 4' would
|
||||
|
|
@ -241,6 +411,20 @@ def encodeFilename(s):
|
|||
else:
|
||||
return s.encode(sys.getfilesystemencoding(), 'ignore')
|
||||
|
||||
|
||||
class ExtractorError(Exception):
|
||||
"""Error during info extraction."""
|
||||
def __init__(self, msg, tb=None):
|
||||
""" tb, if given, is the original traceback (so that it can be printed out). """
|
||||
super(ExtractorError, self).__init__(msg)
|
||||
self.traceback = tb
|
||||
|
||||
def format_traceback(self):
|
||||
if self.traceback is None:
|
||||
return None
|
||||
return u''.join(traceback.format_tb(self.traceback))
|
||||
|
||||
|
||||
class DownloadError(Exception):
|
||||
"""Download Error exception.
|
||||
|
||||
|
|
@ -297,15 +481,7 @@ def __init__(self, downloaded, expected):
|
|||
self.downloaded = downloaded
|
||||
self.expected = expected
|
||||
|
||||
|
||||
class Trouble(Exception):
|
||||
"""Trouble helper exception
|
||||
|
||||
This is an exception to be handled with
|
||||
FileDownloader.trouble
|
||||
"""
|
||||
|
||||
class YoutubeDLHandler(urllib2.HTTPHandler):
|
||||
class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
|
||||
"""Handler for HTTP requests and responses.
|
||||
|
||||
This class, when installed with an OpenerDirector, automatically adds
|
||||
|
|
@ -332,9 +508,9 @@ def deflate(data):
|
|||
|
||||
@staticmethod
|
||||
def addinfourl_wrapper(stream, headers, url, code):
|
||||
if hasattr(urllib2.addinfourl, 'getcode'):
|
||||
return urllib2.addinfourl(stream, headers, url, code)
|
||||
ret = urllib2.addinfourl(stream, headers, url)
|
||||
if hasattr(compat_urllib_request.addinfourl, 'getcode'):
|
||||
return compat_urllib_request.addinfourl(stream, headers, url, code)
|
||||
ret = compat_urllib_request.addinfourl(stream, headers, url)
|
||||
ret.code = code
|
||||
return ret
|
||||
|
||||
|
|
@ -353,12 +529,15 @@ def http_response(self, req, resp):
|
|||
old_resp = resp
|
||||
# gzip
|
||||
if resp.headers.get('Content-encoding', '') == 'gzip':
|
||||
gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
|
||||
gz = gzip.GzipFile(fileobj=io.BytesIO(resp.read()), mode='r')
|
||||
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
|
||||
resp.msg = old_resp.msg
|
||||
# deflate
|
||||
if resp.headers.get('Content-encoding', '') == 'deflate':
|
||||
gz = StringIO.StringIO(self.deflate(resp.read()))
|
||||
gz = io.BytesIO(self.deflate(resp.read()))
|
||||
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
|
||||
resp.msg = old_resp.msg
|
||||
return resp
|
||||
|
||||
https_request = http_request
|
||||
https_response = http_response
|
||||
|
|
|
|||
2
youtube_dl/version.py
Normal file
2
youtube_dl/version.py
Normal file
|
|
@ -0,0 +1,2 @@
|
|||
|
||||
__version__ = '2013.01.02'
|
||||
Loading…
Reference in a new issue