Merge branch 'master' into GoogleDrive-issue-13619

.github/ISSUE_TEMPLATE.md

@@ -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 Issues with outdated version will be rejected.
+### 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 Issues with outdated version will be rejected.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 **2017.08.13**
+- [ ] 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: {}

AUTHORS

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

ChangeLog

@@ -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

docs/supportedsites.md

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

youtube_dl/YoutubeDL.py

@@ -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 url:
-            if not valid_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))

youtube_dl/extractor/arte.py

@@ -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)

youtube_dl/extractor/clippit.py

@@ -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,
+        }

youtube_dl/extractor/extractors.py

@@ -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

youtube_dl/extractor/generic.py

@@ -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

youtube_dl/extractor/mixcloud.py

@@ -91,12 +91,14 @@ class MixcloudIE(InfoExtractor):
             if js_url:
                 js = self._download_webpage(js_url, track_id, fatal=False)
                 if js:
-                    key = self._search_regex(
+                    KEY_RE_TEMPLATE = r'player\s*:\s*{.*?\b%s\s*:\s*(["\'])(?P<key>(?:(?!\1).)+)\1'
-                        r'player\s*:\s*{.*?\bvalue\s*:\s*(["\'])(?P<key>(?:(?!\1).)+)\1',
+                    for key_name in ('value', 'key_value'):
-                        js, 'key', default=None, group='key')
+                        key = self._search_regex(
-                    if key and isinstance(key, compat_str):
+                            KEY_RE_TEMPLATE % key_name, js, 'key',
-                        self._keys.insert(0, key)
+                            default=None, group='key')
-                        self._current_key = key
+                        if key and isinstance(key, compat_str):
+                            self._keys.insert(0, key)
+                            self._current_key = key
 
         message = self._html_search_regex(
             r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',

youtube_dl/extractor/periscope.py

@@ -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 {

youtube_dl/extractor/pluralsight.py

@@ -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(
+        course = self._download_course(course_name, url, display_id)
-            'https://app.pluralsight.com/player/user/api/v1/player/payload',
-            display_id, data=urlencode_postdata({'courseId': course_name}),
-            headers={'Referer': url})
 
         collection = course['modules']
 
@@ -331,18 +362,7 @@ class PluralsightCourseIE(PluralsightBaseIE):
 
         # TODO: PSM cookie
 
-        course = self._download_json(
+        course = self._download_course(course_id, url, course_id)
-            '%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']
 
         title = course['title']
         course_name = course['name']

youtube_dl/extractor/qqmusic.py

@@ -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',
+        'url': 'https://y.qq.com/n/yqq/song/004295Et37taLD.html',
-        'md5': '9ce1c1c8445f561506d2e3cfb0255705',
+        '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_singer_all_songs(self, singmid, num):
-    def get_entries_from_page(cls, page):
+        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):
+        default_num = 1
-            song_mid = unescapeHTML(item).split('|')[-5]
+        json_text = self.get_singer_all_songs(singmid, default_num)
-            entries.append(cls.url_result(
+        json_obj_all_songs = self._parse_json(json_text, singmid)
-                'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
+
-                song_mid))
+        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(
+        entries = self.get_entries_from_page(mid)
-            self.qq_static_url('singer', mid), mid, 'Download singer page')
+        singer_page = self._download_webpage(url, mid, 'Download singer page')
-
-        entries = self.get_entries_from_page(singer_page)
-
         singer_name = self._html_search_regex(
-            r"singername\s*:\s*'([^']+)'", singer_page, 'singer name',
+            r"singername\s*:\s*'(.*?)'", singer_page, 'singer name', default=None)
-            default=None)
-
-        singer_id = self._html_search_regex(
-            r"singerid\s*:\s*'([0-9]+)'", singer_page, 'singer id',
-            default=None)
-
         singer_desc = None
 
-        if singer_id:
+        if mid:
-            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')
             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',
-        },
+            'description': 'md5:89db2335fdbb10678dee2d43fe9aba08',
-        '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'
         },
         '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'
+            'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg', list_id,
-            % (list_type, num_id),
+            note='Download toplist page',
-            list_id, 'Download toplist page')
+            query={'type': 'toplist', 'topid': list_id, 'format': 'json'})
 
-        entries = [
+        entries = [self.url_result(
-            self.url_result(
+            'https://y.qq.com/n/yqq/song/' + song['data']['songmid'] + '.html', 'QQMusic',
-                'http://y.qq.com/#type=song&mid=' + song['data']['songmid'], 'QQMusic', song['data']['songmid']
+            song['data']['songmid'])
-            ) for song in toplist_json['songlist']
+            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'
+            'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg',
-            % list_id, list_id, 'Download list page',
+            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 = [
+        entries = [self.url_result(
-            self.url_result(
+            'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid'])
-                'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
+            for song in cdlist['songlist']]
-            ) for song in cdlist['songlist']
-        ]
 
         list_name = cdlist.get('dissname')
         list_description = clean_html(unescapeHTML(cdlist.get('desc')))

youtube_dl/extractor/udemy.py

@@ -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(

youtube_dl/version.py

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