etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 03:33:02 +00:00
Code Issues Projects Releases Wiki Activity

[mixcloud] Improve and simplify (closes #14132)

Browse source
This commit is contained in:
Sergey M․ 2017-09-23 05:35:55 +07:00
parent 2384f5a64e
commit 095774e591
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 41 additions and 30 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

69
youtube_dl/extractor/mixcloud.py
View file

@ -9,6 +9,7 @@
from ..compat import ( from ..compat import (
compat_chr, compat_chr,
compat_ord, compat_ord,
compat_str,
compat_urllib_parse_unquote, compat_urllib_parse_unquote,
compat_urlparse, compat_urlparse,
compat_zip compat_zip
@ -16,9 +17,12 @@
from ..utils import ( from ..utils import (
clean_html, clean_html,
ExtractorError, ExtractorError,
int_or_none,
OnDemandPagedList, OnDemandPagedList,
str_to_int, str_to_int,
try_get) try_get,
urljoin,
)
class MixcloudIE(InfoExtractor): class MixcloudIE(InfoExtractor):
@ -61,13 +65,6 @@ def _decrypt_xor_cipher(key, ciphertext):
compat_chr(compat_ord(ch) ^ compat_ord(k)) compat_chr(compat_ord(ch) ^ compat_ord(k))
for ch, k in compat_zip(ciphertext, itertools.cycle(key))]) for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
@staticmethod
def _decrypt_and_extend(stream_info, url_key, getter, key, formats):
maybe_url = stream_info.get(url_key)
if maybe_url is not None:
decrypted = MixcloudIE._decrypt_xor_cipher(key, base64.b64decode(maybe_url))
formats.extend(getter(decrypted))
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
uploader = mobj.group(1) uploader = mobj.group(1)
@ -86,9 +83,12 @@ def _real_extract(self, url):
else: else:
# New path # New path
full_info_json = self._parse_json(self._html_search_regex( full_info_json = self._parse_json(self._html_search_regex(
r'<script id="relay-data" type="text/x-mixcloud">([^<]+)</script>', webpage, 'play info'), 'play info') r'<script id="relay-data" type="text/x-mixcloud">([^<]+)</script>',
webpage, 'play info'), 'play info')
for item in full_info_json: for item in full_info_json:
item_data = try_get(item, lambda x: x['cloudcast']['data']['cloudcastLookup']) item_data = try_get(
item, lambda x: x['cloudcast']['data']['cloudcastLookup'],
dict)
if try_get(item_data, lambda x: x['streamInfo']['url']): if try_get(item_data, lambda x: x['streamInfo']['url']):
info_json = item_data info_json = item_data
break break
@ -100,13 +100,9 @@ def _real_extract(self, url):
webpage, 'error message', default=None) webpage, 'error message', default=None)
js_url = self._search_regex( js_url = self._search_regex(
r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/js2/www_js_4\.[^>]+\.js)', r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/(?:js2/www_js_4|js/www)\.[^>]+\.js)',
webpage, 'js url', default=None)
if js_url is None:
js_url = self._search_regex(
r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/js/www\.[^>]+\.js)',
webpage, 'js url') webpage, 'js url')
js = self._download_webpage(js_url, track_id) js = self._download_webpage(js_url, track_id, 'Downloading JS')
# Known plaintext attack # Known plaintext attack
if encrypted_play_info: if encrypted_play_info:
kps = ['{"stream_url":'] kps = ['{"stream_url":']
@ -117,8 +113,9 @@ def _real_extract(self, url):
for kp in kps: for kp in kps:
partial_key = self._decrypt_xor_cipher(kpa_target, kp) partial_key = self._decrypt_xor_cipher(kpa_target, kp)
for quote in ["'", '"']: for quote in ["'", '"']:
key = self._search_regex(r'{0}({1}[^{0}]*){0}'.format(quote, re.escape(partial_key)), js, key = self._search_regex(
"encryption key", default=None) r'{0}({1}[^{0}]*){0}'.format(quote, re.escape(partial_key)),
js, 'encryption key', default=None)
if key is not None: if key is not None:
break break
else: else:
@ -153,23 +150,37 @@ def _real_extract(self, url):
else: else:
title = info_json['name'] title = info_json['name']
thumbnail = try_get(info_json, thumbnail = urljoin(
lambda x: 'https://thumbnailer.mixcloud.com/unsafe/600x600/' + x['picture']['urlRoot']) 'https://thumbnailer.mixcloud.com/unsafe/600x600/',
try_get(info_json, lambda x: x['picture']['urlRoot'], compat_str))
uploader = try_get(info_json, lambda x: x['owner']['displayName']) uploader = try_get(info_json, lambda x: x['owner']['displayName'])
uploader_id = try_get(info_json, lambda x: x['owner']['username']) uploader_id = try_get(info_json, lambda x: x['owner']['username'])
description = try_get(info_json, lambda x: x['description']) description = try_get(info_json, lambda x: x['description'])
view_count = try_get(info_json, lambda x: x['plays']) view_count = int_or_none(try_get(info_json, lambda x: x['plays']))
stream_info = info_json['streamInfo'] stream_info = info_json['streamInfo']
formats = [] formats = []
self._decrypt_and_extend(stream_info, 'url', lambda x: [{
'format_id': 'normal', for url_key in ('url', 'hlsUrl', 'dashUrl'):
'url': x format_url = stream_info.get(url_key)
}], key, formats) if not format_url:
self._decrypt_and_extend(stream_info, 'hlsUrl', lambda x: self._extract_m3u8_formats(x, title), key, continue
formats) decrypted = self._decrypt_xor_cipher(key, base64.b64decode(format_url))
self._decrypt_and_extend(stream_info, 'dashUrl', lambda x: self._extract_mpd_formats(x, title), key, if not decrypted:
formats) continue
if url_key == 'hlsUrl':
formats.extend(self._extract_m3u8_formats(
decrypted, track_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif url_key == 'dashUrl':
formats.extend(self._extract_mpd_formats(
decrypted, track_id, mpd_id='dash', fatal=False))
else:
formats.append({
'format_id': 'http',
'url': decrypted,
})
self._sort_formats(formats)
return { return {
'id': track_id, 'id': track_id,