Merge remote-tracking branch 'upstream/master'

This commit is contained in:
rupertbaxter2 2014-08-13 04:22:45 -07:00
commit f96252b913
15 changed files with 165 additions and 81 deletions

View File

@ -99,6 +99,7 @@ def test_youtube_extract(self):
def test_facebook_matching(self):
self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
self.assertTrue(FacebookIE.suitable('https://www.facebook.com/cindyweather?fref=ts#!/photo.php?v=10152183998945793'))
def test_no_duplicates(self):
ies = gen_extractors()

View File

@ -280,7 +280,7 @@ def test_strip_jsonp(self):
d = json.loads(stripped)
self.assertEqual(d, [{"id": "532cb", "x": 3}])
def test_uppercase_escpae(self):
def test_uppercase_escape(self):
self.assertEqual(uppercase_escape(u''), u'')
self.assertEqual(uppercase_escape(u'\\U0001d550'), u'𝕐')

View File

@ -68,6 +68,7 @@
'Hassaan Ali',
'Dobrosław Żybort',
'David Fabijan',
'Sebastian Haas',
)
__license__ = 'Public Domain'

View File

@ -295,7 +295,7 @@ def download(self, filename, info_dict):
def real_download(self, filename, info_dict):
"""Real download process. Redefine in subclasses."""
raise NotImplementedError(u'This method must be implemented by sublcasses')
raise NotImplementedError(u'This method must be implemented by subclasses')
def _hook_progress(self, status):
for ph in self._progress_hooks:

View File

@ -225,9 +225,12 @@
from .ntv import NTVIE
from .nytimes import NYTimesIE
from .nuvid import NuvidIE
from .oe1 import OE1IE
from .ooyala import OoyalaIE
from .orf import ORFIE
from .orf import (
ORFTVthekIE,
ORFOE1IE,
ORFFM4IE,
)
from .parliamentliveuk import ParliamentLiveUKIE
from .pbs import PBSIE
from .photobucket import PhotobucketIE

View File

@ -6,6 +6,7 @@
from .common import InfoExtractor
from ..utils import (
compat_urlparse,
int_or_none,
)
@ -110,8 +111,8 @@ def _clean_json(m):
formats.append({
'url': format_url,
'format': format['type'],
'width': format['width'],
'height': int(format['height']),
'width': int_or_none(format['width']),
'height': int_or_none(format['height']),
})
self._sort_formats(formats)

View File

@ -51,6 +51,9 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id)
if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
title = self._html_search_regex(
[r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
r'<meta name="dcterms.title" content="(.*?)"/>',

View File

@ -109,15 +109,19 @@ def _match_lang(f):
regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
return any(re.match(r, f['versionCode']) for r in regexes)
# Some formats may not be in the same language as the url
# TODO: Might want not to drop videos that does not match requested language
# but to process those formats with lower precedence
formats = filter(_match_lang, all_formats)
formats = list(formats) # in python3 filter returns an iterator
if not formats:
# Some videos are only available in the 'Originalversion'
# they aren't tagged as being in French or German
if all(f['versionCode'] == 'VO' or f['versionCode'] == 'VA' for f in all_formats):
# Sometimes there are neither videos of requested lang code
# nor original version videos available
# For such cases we just take all_formats as is
formats = all_formats
else:
raise ExtractorError(u'The formats list is empty')
if not formats:
raise ExtractorError('The formats list is empty')
if re.match(r'[A-Z]Q', formats[0]['quality']) is not None:
def sort_key(f):

View File

@ -20,7 +20,7 @@
class FacebookIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://(?:\w+\.)?facebook\.com/
(?:[^#?]*\#!/)?
(?:[^#]*?\#!/)?
(?:video/video\.php|photo\.php|video/embed)\?(?:.*?)
(?:v|video_id)=(?P<id>[0-9]+)
(?:.*)'''

View File

@ -1,40 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import calendar
import datetime
import re
from .common import InfoExtractor
# audios on oe1.orf.at are only available for 7 days, so we can't
# add tests.
class OE1IE(InfoExtractor):
IE_DESC = 'oe1.orf.at'
_VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
show_id = mobj.group('id')
data = self._download_json(
'http://oe1.orf.at/programm/%s/konsole' % show_id,
show_id
)
timestamp = datetime.datetime.strptime('%s %s' % (
data['item']['day_label'],
data['item']['time']
), '%d.%m.%Y %H:%M')
unix_timestamp = calendar.timegm(timestamp.utctimetuple())
return {
'id': show_id,
'title': data['item']['title'],
'url': data['item']['url_stream'],
'ext': 'mp3',
'description': data['item'].get('info'),
'timestamp': unix_timestamp
}

View File

@ -3,13 +3,17 @@
import json
from .common import InfoExtractor
from ..utils import unescapeHTML
from ..utils import (
unescapeHTML,
ExtractorError,
)
class OoyalaIE(InfoExtractor):
_VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)'
_TEST = {
_TESTS = [
{
# From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video
'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
'md5': '3f5cceb3a7bf461d6c29dc466cf8033c',
@ -19,7 +23,18 @@ class OoyalaIE(InfoExtractor):
'title': 'Explaining Data Recovery from Hard Drives and SSDs',
'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
},
}
}, {
# Only available for ipad
'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
'md5': '4b9754921fddb68106e48c142e2a01e6',
'info_dict': {
'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
'ext': 'mp4',
'title': 'Simulation Overview - Levels of Simulation',
'description': '',
},
},
]
@staticmethod
def _url_for_embed_code(embed_code):
@ -47,13 +62,30 @@ def _real_extract(self, url):
player = self._download_webpage(player_url, embedCode)
mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
player, 'mobile player url')
mobile_player = self._download_webpage(mobile_url, embedCode)
# Looks like some videos are only available for particular devices
# (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0
# is only available for ipad)
# Working around with fetching URLs for all the devices found starting with 'unknown'
# until we succeed or eventually fail for each device.
devices = re.findall(r'device\s*=\s*"([^"]+)";', player)
devices.remove('unknown')
devices.insert(0, 'unknown')
for device in devices:
mobile_player = self._download_webpage(
'%s&device=%s' % (mobile_url, device), embedCode,
'Downloading mobile player JS for %s device' % device)
videos_info = self._search_regex(
r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
mobile_player, 'info').replace('\\"','"')
videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"','"')
mobile_player, 'info', fatal=False, default=None)
if videos_info:
break
if not videos_info:
raise ExtractorError('Unable to extract info')
videos_info = videos_info.replace('\\"', '"')
videos_more_info = self._search_regex(
r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"')
videos_info = json.loads(videos_info)
videos_more_info =json.loads(videos_more_info)
videos_more_info = json.loads(videos_more_info)
if videos_more_info.get('lineup'):
videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]

View File

@ -3,6 +3,8 @@
import json
import re
import calendar
import datetime
from .common import InfoExtractor
from ..utils import (
@ -12,7 +14,9 @@
)
class ORFIE(InfoExtractor):
class ORFTVthekIE(InfoExtractor):
IE_NAME = 'orf:tvthek'
IE_DESC = 'ORF TVthek'
_VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)'
_TEST = {
@ -105,3 +109,73 @@ def quality_to_int(s):
'entries': entries,
'id': playlist_id,
}
# Audios on ORF radio are only available for 7 days, so we can't add tests.
class ORFOE1IE(InfoExtractor):
IE_NAME = 'orf:oe1'
IE_DESC = 'Radio Österreich 1'
_VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
show_id = mobj.group('id')
data = self._download_json(
'http://oe1.orf.at/programm/%s/konsole' % show_id,
show_id
)
timestamp = datetime.datetime.strptime('%s %s' % (
data['item']['day_label'],
data['item']['time']
), '%d.%m.%Y %H:%M')
unix_timestamp = calendar.timegm(timestamp.utctimetuple())
return {
'id': show_id,
'title': data['item']['title'],
'url': data['item']['url_stream'],
'ext': 'mp3',
'description': data['item'].get('info'),
'timestamp': unix_timestamp
}
class ORFFM4IE(InfoExtractor):
IE_DESC = 'orf:fm4'
IE_DESC = 'radio FM4'
_VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
show_date = mobj.group('date')
show_id = mobj.group('show')
data = self._download_json(
'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id),
show_id
)
def extract_entry_dict(info, title, subtitle):
return {
'id': info['loopStreamId'].replace('.mp3', ''),
'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info['loopStreamId'],
'title': title,
'description': subtitle,
'duration': (info['end'] - info['start']) / 1000,
'timestamp': info['start'] / 1000,
'ext': 'mp3'
}
entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]
return {
'_type': 'playlist',
'id': show_id,
'title': data['title'],
'description': data['subtitle'],
'entries': entries
}

View File

@ -1,23 +1,23 @@
from __future__ import unicode_literals
import re
import time
from .common import InfoExtractor
from ..utils import strip_jsonp
from ..utils import str_or_none
class ReverbNationIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
_TESTS = [{
'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa',
'file': '16965047.mp3',
'md5': '3da12ebca28c67c111a7f8b262d3f7a7',
'info_dict': {
"id": "16965047",
"ext": "mp3",
"title": "MONA LISA",
"uploader": "ALKILADOS",
"uploader_id": 216429,
"thumbnail": "//gp1.wac.edgecastcdn.net/802892/production_public/Photo/13761700/image/1366002176_AVATAR_MONA_LISA.jpg"
"uploader_id": "216429",
"thumbnail": "re:^https://gp1\.wac\.edgecastcdn\.net/.*?\.jpg$"
},
}]
@ -26,10 +26,8 @@ def _real_extract(self, url):
song_id = mobj.group('id')
api_res = self._download_json(
'https://api.reverbnation.com/song/%s?callback=api_response_5&_=%d'
% (song_id, int(time.time() * 1000)),
'https://api.reverbnation.com/song/%s' % song_id,
song_id,
transform_source=strip_jsonp,
note='Downloading information of song %s' % song_id
)
@ -38,8 +36,9 @@ def _real_extract(self, url):
'title': api_res.get('name'),
'url': api_res.get('url'),
'uploader': api_res.get('artist', {}).get('name'),
'uploader_id': api_res.get('artist', {}).get('id'),
'thumbnail': api_res.get('image', api_res.get('thumbnail')),
'uploader_id': str_or_none(api_res.get('artist', {}).get('id')),
'thumbnail': self._proto_relative_url(
api_res.get('image', api_res.get('thumbnail'))),
'ext': 'mp3',
'vcodec': 'none',
}

View File

@ -1273,9 +1273,15 @@ def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1):
if get_attr:
if v is not None:
v = getattr(v, get_attr, None)
if v == '':
v = None
return default if v is None else (int(v) * invscale // scale)
def str_or_none(v, default=None):
return default if v is None else compat_str(v)
def str_to_int(int_str):
if int_str is None:
return None

View File

@ -1,2 +1,2 @@
__version__ = '2014.08.05'
__version__ = '2014.08.10'