R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'master' into GoogleDrive-issue-13619

Browse Source
This commit is contained in:
Parmjit Virk 2017-08-18 15:52:05 -05:00
commit 4687757aa1
15 changed files with 262 additions and 121 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/ISSUE_TEMPLATE.md vendored
View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.08.13*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.08.13**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.08.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.08.18**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2017.08.13
[debug] youtube-dl version 2017.08.18
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

1
AUTHORS
View File

@ -223,3 +223,4 @@ Jan Kundrát
Giuseppe Fabiano
Örn Guðjónsson
Parmjit Virk
Genki Sky

18
ChangeLog
View File

@ -1,3 +1,21 @@
version 2017.08.18
Core
* [YoutubeDL] Sanitize byte string format URLs (#13951)
+ [extractor/common] Add support for float durations in _parse_mpd_formats
(#13919)
Extractors
* [arte] Detect unavailable videos (#13945)
* [generic] Convert redirect URLs to unicode strings (#13951)
* [udemy] Fix paid course detection (#13943)
* [pluralsight] Use RPC API for course extraction (#13937)
+ [clippit] Add support for clippituser.tv
+ [qqmusic] Support new URL schemes (#13805)
* [periscope] Renew HLS extraction (#13917)
* [mixcloud] Extract decrypt key
version 2017.08.13
Core

1
docs/supportedsites.md
View File

@ -156,6 +156,7 @@
- **Cinchcast**
- **CJSW**
- **cliphunter**
- **Clippit**
- **ClipRs**
- **Clipsyndicate**
- **CloserToTruth**

8
youtube_dl/YoutubeDL.py
View File

@ -1483,12 +1483,14 @@ class YoutubeDL(object):
def is_wellformed(f):
url = f.get('url')
valid_url = url and isinstance(url, compat_str)
if not valid_url:
if not url:
self.report_warning(
'"url" field is missing or empty - skipping format, '
'there is an error in extractor')
return valid_url
return False
if isinstance(url, bytes):
sanitize_string_field(f, 'url')
return True
# Filter out malformed formats for better extraction robustness
formats = list(filter(is_wellformed, formats))

12
youtube_dl/extractor/arte.py
View File

@ -9,12 +9,13 @@ from ..compat import (
compat_urllib_parse_urlparse,
)
from ..utils import (
ExtractorError,
find_xpath_attr,
unified_strdate,
get_element_by_attribute,
int_or_none,
NO_DEFAULT,
qualities,
unified_strdate,
)
# There are different sources of video in arte.tv, the extraction process
@ -79,6 +80,13 @@ class ArteTVBaseIE(InfoExtractor):
info = self._download_json(json_url, video_id)
player_info = info['videoJsonPlayer']
vsr = player_info['VSR']
if not vsr and not player_info.get('VRU'):
raise ExtractorError(
'Video %s is not available' % player_info.get('VID') or video_id,
expected=True)
upload_date_str = player_info.get('shootingDate')
if not upload_date_str:
upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0]
@ -107,7 +115,7 @@ class ArteTVBaseIE(InfoExtractor):
langcode = LANGS.get(lang, lang)
formats = []
for format_id, format_dict in player_info['VSR'].items():
for format_id, format_dict in vsr.items():
f = dict(format_dict)
versionCode = f.get('versionCode')
l = re.escape(langcode)

74
youtube_dl/extractor/clippit.py Normal file
View File

@ -0,0 +1,74 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
qualities,
)
import re
class ClippitIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?clippituser\.tv/c/(?P<id>[a-z]+)'
_TEST = {
'url': 'https://www.clippituser.tv/c/evmgm',
'md5': '963ae7a59a2ec4572ab8bf2f2d2c5f09',
'info_dict': {
'id': 'evmgm',
'ext': 'mp4',
'title': 'Bye bye Brutus. #BattleBots - Clippit',
'uploader': 'lizllove',
'uploader_url': 'https://www.clippituser.tv/p/lizllove',
'timestamp': 1472183818,
'upload_date': '20160826',
'description': 'BattleBots | ABC',
'thumbnail': r're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title.*>(.+?)</title>', webpage, 'title')
FORMATS = ('sd', 'hd')
quality = qualities(FORMATS)
formats = []
for format_id in FORMATS:
url = self._html_search_regex(r'data-%s-file="(.+?)"' % format_id,
webpage, 'url', fatal=False)
if not url:
continue
match = re.search(r'/(?P<height>\d+)\.mp4', url)
formats.append({
'url': url,
'format_id': format_id,
'quality': quality(format_id),
'height': int(match.group('height')) if match else None,
})
uploader = self._html_search_regex(r'class="username".*>\s+(.+?)\n',
webpage, 'uploader', fatal=False)
uploader_url = ('https://www.clippituser.tv/p/' + uploader
if uploader else None)
timestamp = self._html_search_regex(r'datetime="(.+?)"',
webpage, 'date', fatal=False)
thumbnail = self._html_search_regex(r'data-image="(.+?)"',
webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'title': title,
'formats': formats,
'uploader': uploader,
'uploader_url': uploader_url,
'timestamp': parse_iso8601(timestamp),
'description': self._og_search_description(webpage),
'thumbnail': thumbnail,
}

1
youtube_dl/extractor/extractors.py
View File

@ -187,6 +187,7 @@ from .chirbit import (
from .cinchcast import CinchcastIE
from .cjsw import CJSWIE
from .cliphunter import CliphunterIE
from .clippit import ClippitIE
from .cliprs import ClipRsIE
from .clipsyndicate import ClipsyndicateIE
from .closertotruth import CloserToTruthIE

4
youtube_dl/extractor/generic.py
View File

@ -2015,7 +2015,7 @@ class GenericIE(InfoExtractor):
if head_response is not False:
# Check for redirect
new_url = head_response.geturl()
new_url = compat_str(head_response.geturl())
if url != new_url:
self.report_following_redirect(new_url)
if force_videoid:
@ -2116,7 +2116,7 @@ class GenericIE(InfoExtractor):
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'] = self._parse_mpd_formats(
doc, video_id,
mpd_base_url=full_response.geturl().rpartition('/')[0],
mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
mpd_url=url)
self._sort_formats(info_dict['formats'])
return info_dict

6
youtube_dl/extractor/mixcloud.py
View File

@ -91,9 +91,11 @@ class MixcloudIE(InfoExtractor):
if js_url:
js = self._download_webpage(js_url, track_id, fatal=False)
if js:
KEY_RE_TEMPLATE = r'player\s*:\s*{.*?\b%s\s*:\s*(["\'])(?P<key>(?:(?!\1).)+)\1'
for key_name in ('value', 'key_value'):
key = self._search_regex(
r'player\s*:\s*{.*?\bvalue\s*:\s*(["\'])(?P<key>(?:(?!\1).)+)\1',
js, 'key', default=None, group='key')
KEY_RE_TEMPLATE % key_name, js, 'key',
default=None, group='key')
if key and isinstance(key, compat_str):
self._keys.insert(0, key)
self._current_key = key

20
youtube_dl/extractor/periscope.py
View File

@ -80,18 +80,24 @@ class PeriscopeIE(PeriscopeBaseIE):
stream = self._call_api(
'getAccessPublic', {'broadcast_id': token}, token)
video_urls = set()
formats = []
for format_id in ('replay', 'rtmp', 'hls', 'https_hls'):
for format_id in ('replay', 'rtmp', 'hls', 'https_hls', 'lhls', 'lhlsweb'):
video_url = stream.get(format_id + '_url')
if not video_url:
if not video_url or video_url in video_urls:
continue
f = {
video_urls.add(video_url)
if format_id != 'rtmp':
formats.extend(self._extract_m3u8_formats(
video_url, token, 'mp4',
entry_protocol='m3u8_native'
if state in ('ended', 'timed_out') else 'm3u8',
m3u8_id=format_id, fatal=False))
continue
formats.append({
'url': video_url,
'ext': 'flv' if format_id == 'rtmp' else 'mp4',
}
if format_id != 'rtmp':
f['protocol'] = 'm3u8_native' if state in ('ended', 'timed_out') else 'm3u8'
formats.append(f)
})
self._sort_formats(formats)
return {

52
youtube_dl/extractor/pluralsight.py
View File

@ -18,6 +18,7 @@ from ..utils import (
parse_duration,
qualities,
srt_subtitles_timecode,
try_get,
update_url_query,
urlencode_postdata,
)
@ -26,6 +27,39 @@ from ..utils import (
class PluralsightBaseIE(InfoExtractor):
_API_BASE = 'https://app.pluralsight.com'
def _download_course(self, course_id, url, display_id):
try:
return self._download_course_rpc(course_id, url, display_id)
except ExtractorError:
# Old API fallback
return self._download_json(
'https://app.pluralsight.com/player/user/api/v1/player/payload',
display_id, data=urlencode_postdata({'courseId': course_id}),
headers={'Referer': url})
def _download_course_rpc(self, course_id, url, display_id):
response = self._download_json(
'%s/player/functions/rpc' % self._API_BASE, display_id,
'Downloading course JSON',
data=json.dumps({
'fn': 'bootstrapPlayer',
'payload': {
'courseId': course_id,
},
}).encode('utf-8'),
headers={
'Content-Type': 'application/json;charset=utf-8',
'Referer': url,
})
course = try_get(response, lambda x: x['payload']['course'], dict)
if course:
return course
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, response['error']['message']),
expected=True)
class PluralsightIE(PluralsightBaseIE):
IE_NAME = 'pluralsight'
@ -162,10 +196,7 @@ class PluralsightIE(PluralsightBaseIE):
display_id = '%s-%s' % (name, clip_id)
course = self._download_json(
'https://app.pluralsight.com/player/user/api/v1/player/payload',
display_id, data=urlencode_postdata({'courseId': course_name}),
headers={'Referer': url})
course = self._download_course(course_name, url, display_id)
collection = course['modules']
@ -331,18 +362,7 @@ class PluralsightCourseIE(PluralsightBaseIE):
# TODO: PSM cookie
course = self._download_json(
'%s/player/functions/rpc' % self._API_BASE, course_id,
'Downloading course JSON',
data=json.dumps({
'fn': 'bootstrapPlayer',
'payload': {
'courseId': course_id,
}
}).encode('utf-8'),
headers={
'Content-Type': 'application/json;charset=utf-8'
})['payload']['course']
course = self._download_course(course_id, url, course_id)
title = course['title']
course_name = course['name']

168
youtube_dl/extractor/qqmusic.py
View File

@ -2,38 +2,37 @@
from __future__ import unicode_literals
import random
import time
import re
import time
from .common import InfoExtractor
from ..utils import (
sanitized_Request,
strip_jsonp,
unescapeHTML,
clean_html,
ExtractorError,
strip_jsonp,
unescapeHTML,
)
class QQMusicIE(InfoExtractor):
IE_NAME = 'qqmusic'
IE_DESC = 'QQ音乐'
_VALID_URL = r'https?://y\.qq\.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
_VALID_URL = r'https?://y\.qq\.com/n/yqq/song/(?P<id>[0-9A-Za-z]+)\.html'
_TESTS = [{
'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
'md5': '9ce1c1c8445f561506d2e3cfb0255705',
'url': 'https://y.qq.com/n/yqq/song/004295Et37taLD.html',
'md5': '5f1e6cea39e182857da7ffc5ef5e6bb8',
'info_dict': {
'id': '004295Et37taLD',
'ext': 'mp3',
'title': '可惜没如果',
'release_date': '20141227',
'creator': '林俊杰',
'description': 'md5:d327722d0361576fde558f1ac68a7065',
'description': 'md5:d85afb3051952ecc50a1ee8a286d1eac',
'thumbnail': r're:^https?://.*\.jpg$',
}
}, {
'note': 'There is no mp3-320 version of this song.',
'url': 'http://y.qq.com/#type=song&mid=004MsGEo3DdNxV',
'url': 'https://y.qq.com/n/yqq/song/004MsGEo3DdNxV.html',
'md5': 'fa3926f0c585cda0af8fa4f796482e3e',
'info_dict': {
'id': '004MsGEo3DdNxV',
@ -46,14 +45,14 @@ class QQMusicIE(InfoExtractor):
}
}, {
'note': 'lyrics not in .lrc format',
'url': 'http://y.qq.com/#type=song&mid=001JyApY11tIp6',
'url': 'https://y.qq.com/n/yqq/song/001JyApY11tIp6.html',
'info_dict': {
'id': '001JyApY11tIp6',
'ext': 'mp3',
'title': 'Shadows Over Transylvania',
'release_date': '19970225',
'creator': 'Dark Funeral',
'description': 'md5:ed14d5bd7ecec19609108052c25b2c11',
'description': 'md5:c9b20210587cbcd6836a1c597bab4525',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {
@ -105,7 +104,7 @@ class QQMusicIE(InfoExtractor):
[r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'],
detail_info_page, 'album mid', default=None)
if albummid:
thumbnail_url = "http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg" \
thumbnail_url = 'http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg' \
% (albummid[-2:-1], albummid[-1], albummid)
guid = self.m_r_get_ruin()
@ -156,15 +155,39 @@ class QQPlaylistBaseIE(InfoExtractor):
def qq_static_url(category, mid):
return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category, mid[-2], mid[-1], mid)
@classmethod
def get_entries_from_page(cls, page):
def get_singer_all_songs(self, singmid, num):
return self._download_webpage(
r'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg', singmid,
query={
'format': 'json',
'inCharset': 'utf8',
'outCharset': 'utf-8',
'platform': 'yqq',
'needNewCode': 0,
'singermid': singmid,
'order': 'listen',
'begin': 0,
'num': num,
'songstatus': 1,
})
def get_entries_from_page(self, singmid):
entries = []
for item in re.findall(r'class="data"[^<>]*>([^<>]+)</', page):
song_mid = unescapeHTML(item).split('|')[-5]
entries.append(cls.url_result(
'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
song_mid))
default_num = 1
json_text = self.get_singer_all_songs(singmid, default_num)
json_obj_all_songs = self._parse_json(json_text, singmid)
if json_obj_all_songs['code'] == 0:
total = json_obj_all_songs['data']['total']
json_text = self.get_singer_all_songs(singmid, total)
json_obj_all_songs = self._parse_json(json_text, singmid)
for item in json_obj_all_songs['data']['list']:
if item['musicData'].get('songmid') is not None:
songmid = item['musicData']['songmid']
entries.append(self.url_result(
r'https://y.qq.com/n/yqq/song/%s.html' % songmid, 'QQMusic', songmid))
return entries
@ -172,42 +195,32 @@ class QQPlaylistBaseIE(InfoExtractor):
class QQMusicSingerIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:singer'
IE_DESC = 'QQ音乐 - 歌手'
_VALID_URL = r'https?://y\.qq\.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
_VALID_URL = r'https?://y\.qq\.com/n/yqq/singer/(?P<id>[0-9A-Za-z]+)\.html'
_TEST = {
'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
'url': 'https://y.qq.com/n/yqq/singer/001BLpXF2DyJe2.html',
'info_dict': {
'id': '001BLpXF2DyJe2',
'title': '林俊杰',
'description': 'md5:870ec08f7d8547c29c93010899103751',
},
'playlist_count': 12,
'playlist_mincount': 12,
}
def _real_extract(self, url):
mid = self._match_id(url)
singer_page = self._download_webpage(
self.qq_static_url('singer', mid), mid, 'Download singer page')
entries = self.get_entries_from_page(singer_page)
entries = self.get_entries_from_page(mid)
singer_page = self._download_webpage(url, mid, 'Download singer page')
singer_name = self._html_search_regex(
r"singername\s*:\s*'([^']+)'", singer_page, 'singer name',
default=None)
singer_id = self._html_search_regex(
r"singerid\s*:\s*'([0-9]+)'", singer_page, 'singer id',
default=None)
r"singername\s*:\s*'(.*?)'", singer_page, 'singer name', default=None)
singer_desc = None
if singer_id:
req = sanitized_Request(
'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id)
req.add_header(
'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
if mid:
singer_desc_page = self._download_xml(
req, mid, 'Donwload singer description XML')
'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg', mid,
'Donwload singer description XML',
query={'utf8': 1, 'outCharset': 'utf-8', 'format': 'xml', 'singermid': mid},
headers={'Referer': 'https://y.qq.com/n/yqq/singer/'})
singer_desc = singer_desc_page.find('./data/info/desc').text
@ -217,10 +230,10 @@ class QQMusicSingerIE(QQPlaylistBaseIE):
class QQMusicAlbumIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:album'
IE_DESC = 'QQ音乐 - 专辑'
_VALID_URL = r'https?://y\.qq\.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
_VALID_URL = r'https?://y\.qq\.com/n/yqq/album/(?P<id>[0-9A-Za-z]+)\.html'
_TESTS = [{
'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',
'url': 'https://y.qq.com/n/yqq/album/000gXCTb2AhRR1.html',
'info_dict': {
'id': '000gXCTb2AhRR1',
'title': '我们都是这样长大的',
@ -228,7 +241,7 @@ class QQMusicAlbumIE(QQPlaylistBaseIE):
},
'playlist_count': 4,
}, {
'url': 'http://y.qq.com/#type=album&mid=002Y5a3b3AlCu3',
'url': 'https://y.qq.com/n/yqq/album/002Y5a3b3AlCu3.html',
'info_dict': {
'id': '002Y5a3b3AlCu3',
'title': '그리고...',
@ -246,7 +259,7 @@ class QQMusicAlbumIE(QQPlaylistBaseIE):
entries = [
self.url_result(
'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid']
) for song in album['list']
]
album_name = album.get('name')
@ -260,31 +273,30 @@ class QQMusicAlbumIE(QQPlaylistBaseIE):
class QQMusicToplistIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:toplist'
IE_DESC = 'QQ音乐 - 排行榜'
_VALID_URL = r'https?://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
_VALID_URL = r'https?://y\.qq\.com/n/yqq/toplist/(?P<id>[0-9]+)\.html'
_TESTS = [{
'url': 'http://y.qq.com/#type=toplist&p=global_123',
'url': 'https://y.qq.com/n/yqq/toplist/123.html',
'info_dict': {
'id': 'global_123',
'id': '123',
'title': '美国iTunes榜',
},
'playlist_count': 10,
}, {
'url': 'http://y.qq.com/#type=toplist&p=top_3',
'info_dict': {
'id': 'top_3',
'title': '巅峰榜·欧美',
'description': 'QQ音乐巅峰榜·欧美根据用户收听行为自动生成，集结当下最流行的欧美新歌！:更新时间：每周四22点|统'
'计周期：一周（上周四至本周三）|统计对象：三个月内发行的欧美歌曲|统计数量：100首|统计算法：根据'
'歌曲在一周内的有效播放次数，由高到低取前100名（同一歌手最多允许5首歌曲同时上榜）|有效播放次数：'
'登录用户完整播放一首歌曲，记为一次有效播放；同一用户收听同一首歌曲，每天记录为1次有效播放'
'description': 'md5:89db2335fdbb10678dee2d43fe9aba08',
},
'playlist_count': 100,
}, {
'url': 'http://y.qq.com/#type=toplist&p=global_106',
'url': 'https://y.qq.com/n/yqq/toplist/3.html',
'info_dict': {
'id': 'global_106',
'id': '3',
'title': '巅峰榜·欧美',
'description': 'md5:5a600d42c01696b26b71f8c4d43407da',
},
'playlist_count': 100,
}, {
'url': 'https://y.qq.com/n/yqq/toplist/106.html',
'info_dict': {
'id': '106',
'title': '韩国Mnet榜',
'description': 'md5:cb84b325215e1d21708c615cac82a6e7',
},
'playlist_count': 50,
}]
@ -292,18 +304,15 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
def _real_extract(self, url):
list_id = self._match_id(url)
list_type, num_id = list_id.split("_")
toplist_json = self._download_json(
'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg?type=%s&topid=%s&format=json'
% (list_type, num_id),
list_id, 'Download toplist page')
'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg', list_id,
note='Download toplist page',
query={'type': 'toplist', 'topid': list_id, 'format': 'json'})
entries = [
self.url_result(
'http://y.qq.com/#type=song&mid=' + song['data']['songmid'], 'QQMusic', song['data']['songmid']
) for song in toplist_json['songlist']
]
entries = [self.url_result(
'https://y.qq.com/n/yqq/song/' + song['data']['songmid'] + '.html', 'QQMusic',
song['data']['songmid'])
for song in toplist_json['songlist']]
topinfo = toplist_json.get('topinfo', {})
list_name = topinfo.get('ListName')
@ -314,10 +323,10 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
class QQMusicPlaylistIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:playlist'
IE_DESC = 'QQ音乐 - 歌单'
_VALID_URL = r'https?://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'
_VALID_URL = r'https?://y\.qq\.com/n/yqq/playlist/(?P<id>[0-9]+)\.html'
_TESTS = [{
'url': 'http://y.qq.com/#type=taoge&id=3462654915',
'url': 'http://y.qq.com/n/yqq/playlist/3462654915.html',
'info_dict': {
'id': '3462654915',
'title': '韩国5月新歌精选下旬',
@ -326,7 +335,7 @@ class QQMusicPlaylistIE(QQPlaylistBaseIE):
'playlist_count': 40,
'skip': 'playlist gone',
}, {
'url': 'http://y.qq.com/#type=taoge&id=1374105607',
'url': 'https://y.qq.com/n/yqq/playlist/1374105607.html',
'info_dict': {
'id': '1374105607',
'title': '易入人心的华语民谣',
@ -339,8 +348,9 @@ class QQMusicPlaylistIE(QQPlaylistBaseIE):
list_id = self._match_id(url)
list_json = self._download_json(
'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg?type=1&json=1&utf8=1&onlysong=0&disstid=%s'
% list_id, list_id, 'Download list page',
'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg',
list_id, 'Download list page',
query={'type': 1, 'json': 1, 'utf8': 1, 'onlysong': 0, 'disstid': list_id},
transform_source=strip_jsonp)
if not len(list_json.get('cdlist', [])):
if list_json.get('code'):
@ -350,11 +360,9 @@ class QQMusicPlaylistIE(QQPlaylistBaseIE):
raise ExtractorError('Unable to get playlist info')
cdlist = list_json['cdlist'][0]
entries = [
self.url_result(
'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
) for song in cdlist['songlist']
]
entries = [self.url_result(
'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid'])
for song in cdlist['songlist']]
list_name = cdlist.get('dissname')
list_description = clean_html(unescapeHTML(cdlist.get('desc')))

2
youtube_dl/extractor/udemy.py
View File

@ -74,7 +74,7 @@ class UdemyIE(InfoExtractor):
return compat_urlparse.urljoin(base_url, url) if not url.startswith('http') else url
checkout_url = unescapeHTML(self._search_regex(
r'href=(["\'])(?P<url>(?:https?://(?:www\.)?udemy\.com)?/payment/checkout/.+?)\1',
r'href=(["\'])(?P<url>(?:https?://(?:www\.)?udemy\.com)?/(?:payment|cart)/checkout/.+?)\1',
webpage, 'checkout url', group='url', default=None))
if checkout_url:
raise ExtractorError(

2
youtube_dl/version.py
View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2017.08.13'
__version__ = '2017.08.18'