aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/empflix.py2
-rw-r--r--youtube_dl/extractor/qqmusic.py60
-rw-r--r--youtube_dl/extractor/teamcoco.py29
-rw-r--r--youtube_dl/extractor/tnaflix.py12
4 files changed, 58 insertions, 45 deletions
diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py
index 9a5a8f4bb..4827022e0 100644
--- a/youtube_dl/extractor/empflix.py
+++ b/youtube_dl/extractor/empflix.py
@@ -26,6 +26,6 @@ class EMPFlixIE(TNAFlixIE):
},
{
'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
- 'matching_only': True,
+ 'only_matching': True,
}
]
diff --git a/youtube_dl/extractor/qqmusic.py b/youtube_dl/extractor/qqmusic.py
index dc300e189..e24ddaefe 100644
--- a/youtube_dl/extractor/qqmusic.py
+++ b/youtube_dl/extractor/qqmusic.py
@@ -9,7 +9,6 @@ from .common import InfoExtractor
from ..utils import (
strip_jsonp,
unescapeHTML,
- js_to_json,
)
from ..compat import compat_urllib_request
@@ -196,60 +195,49 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
_VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
_TESTS = [{
- 'url': 'http://y.qq.com/#type=toplist&p=global_12',
+ 'url': 'http://y.qq.com/#type=toplist&p=global_123',
'info_dict': {
- 'id': 'global_12',
- 'title': 'itunes榜',
+ 'id': 'global_123',
+ 'title': '美国iTunes榜',
},
'playlist_count': 10,
}, {
- 'url': 'http://y.qq.com/#type=toplist&p=top_6',
+ 'url': 'http://y.qq.com/#type=toplist&p=top_3',
'info_dict': {
- 'id': 'top_6',
+ 'id': 'top_3',
'title': 'QQ音乐巅峰榜·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_5',
+ 'url': 'http://y.qq.com/#type=toplist&p=global_106',
'info_dict': {
- 'id': 'global_5',
- 'title': '韩国mnet排行榜',
+ 'id': 'global_106',
+ 'title': '韩国Mnet榜',
},
'playlist_count': 50,
}]
- @staticmethod
- def strip_qq_jsonp(code):
- return js_to_json(re.sub(r'^MusicJsonCallback\((.*?)\)/\*.+?\*/$', r'\1', code))
-
def _real_extract(self, url):
list_id = self._match_id(url)
list_type, num_id = list_id.split("_")
- list_page = self._download_webpage(
- "http://y.qq.com/y/static/toplist/index/%s.html" % list_id,
- list_id, 'Download toplist page')
-
- entries = []
- if list_type == 'top':
- jsonp_url = "http://y.qq.com/y/static/toplist/json/top/%s/1.js" % num_id
- else:
- jsonp_url = "http://y.qq.com/y/static/toplist/json/global/%s/1_1.js" % num_id
-
toplist_json = self._download_json(
- jsonp_url, list_id, note='Retrieve toplist json',
- errnote='Unable to get toplist json', transform_source=self.strip_qq_jsonp)
-
- for song in toplist_json['l']:
- s = song['s']
- song_mid = s.split("|")[20]
- entries.append(self.url_result(
- 'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
- song_mid))
+ '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')
- list_name = self._html_search_regex(
- r'<h2 id="top_name">([^\']+)</h2>', list_page, 'top list name',
- default=None)
+ entries = [
+ self.url_result(
+ 'http://y.qq.com/#type=song&mid=' + song['data']['songmid'], 'QQMusic', song['data']['songmid']
+ ) for song in toplist_json['songlist']
+ ]
- return self.playlist_result(entries, list_id, list_name)
+ topinfo = toplist_json.get('topinfo', {})
+ list_name = topinfo.get('ListName')
+ list_description = topinfo.get('info')
+ return self.playlist_result(entries, list_id, list_name, list_description)
diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py
index b2a4b1fc0..d1b7264b4 100644
--- a/youtube_dl/extractor/teamcoco.py
+++ b/youtube_dl/extractor/teamcoco.py
@@ -51,6 +51,17 @@ class TeamcocoIE(InfoExtractor):
'params': {
'skip_download': True, # m3u8 downloads
}
+ }, {
+ 'url': 'http://teamcoco.com/video/full-episode-mon-6-1-joel-mchale-jake-tapper-and-musical-guest-courtney-barnett?playlist=x;eyJ0eXBlIjoidGFnIiwiaWQiOjl9',
+ 'info_dict': {
+ 'id': '89341',
+ 'ext': 'mp4',
+ 'title': 'Full Episode - Mon. 6/1 - Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett',
+ 'description': 'Guests: Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett',
+ },
+ 'params': {
+ 'skip_download': True, # m3u8 downloads
+ }
}
]
_VIDEO_ID_REGEXES = (
@@ -110,9 +121,23 @@ class TeamcocoIE(InfoExtractor):
get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
for filed in data['files']:
if determine_ext(filed['url']) == 'm3u8':
- formats.extend(self._extract_m3u8_formats(
- filed['url'], video_id, ext='mp4'))
+ # compat_urllib_parse.urljoin does not work here
+ if filed['url'].startswith('/'):
+ m3u8_url = 'http://ht.cdn.turner.com/tbs/big/teamcoco' + filed['url']
+ else:
+ m3u8_url = filed['url']
+ m3u8_formats = self._extract_m3u8_formats(
+ m3u8_url, video_id, ext='mp4')
+ for m3u8_format in m3u8_formats:
+ if m3u8_format not in formats:
+ formats.append(m3u8_format)
+ elif determine_ext(filed['url']) == 'f4m':
+ # TODO Correct f4m extraction
+ continue
else:
+ if filed['url'].startswith('/mp4:protected/'):
+ # TODO Correct extraction for these files
+ continue
m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
if m_format is not None:
format_id = m_format.group(1)
diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py
index 59af9aba0..c282865b2 100644
--- a/youtube_dl/extractor/tnaflix.py
+++ b/youtube_dl/extractor/tnaflix.py
@@ -33,7 +33,7 @@ class TNAFlixIE(InfoExtractor):
},
{
'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
- 'matching_only': True,
+ 'only_matching': True,
}
]
@@ -51,9 +51,8 @@ class TNAFlixIE(InfoExtractor):
age_limit = self._rta_search(webpage)
- duration = self._html_search_meta('duration', webpage, 'duration', default=None)
- if duration:
- duration = parse_duration(duration[1:])
+ duration = parse_duration(self._html_search_meta(
+ 'duration', webpage, 'duration', default=None))
cfg_url = self._proto_relative_url(self._html_search_regex(
self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
@@ -62,14 +61,15 @@ class TNAFlixIE(InfoExtractor):
cfg_url, display_id, note='Downloading metadata',
transform_source=fix_xml_ampersands)
- thumbnail = cfg_xml.find('./startThumb').text
+ thumbnail = self._proto_relative_url(
+ cfg_xml.find('./startThumb').text, 'http:')
formats = []
for item in cfg_xml.findall('./quality/item'):
video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text)
format_id = item.find('res').text
fmt = {
- 'url': video_url,
+ 'url': self._proto_relative_url(video_url, 'http:'),
'format_id': format_id,
}
m = re.search(r'^(\d+)', format_id)
generated by cgit v1.2.3 (git 2.26.2) at 2024-07-16 14:16:11 +0000