[youjizz] Fix extraction. The site has moved to HTML5

Closes #10437
This commit is contained in:
Yen Chi Hsuan 2016-09-03 18:37:36 +08:00
parent ed2bfe93aa
commit 45aab4d30b
No known key found for this signature in database
GPG Key ID: 3FDDD575826C5C30
2 changed files with 10 additions and 34 deletions

View File

@ -1,6 +1,7 @@
version <unreleased> version <unreleased>
Extractors Extractors
* [youjizz] Fix extraction (#10437)
+ [foxnews] Add support for FoxNews Insider (#10445) + [foxnews] Add support for FoxNews Insider (#10445)
+ [fc2] Recognize Flash player URLs (#10512) + [fc2] Recognize Flash player URLs (#10512)

View File

@ -1,21 +1,16 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class YouJizzIE(InfoExtractor): class YouJizzIE(InfoExtractor):
_VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/(?:[^/#?]+)?-(?P<id>[0-9]+)\.html(?:$|[?#])' _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/(?:[^/#?]+)?-(?P<id>[0-9]+)\.html(?:$|[?#])'
_TESTS = [{ _TESTS = [{
'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html', 'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
'md5': '07e15fa469ba384c7693fd246905547c', 'md5': '78fc1901148284c69af12640e01c6310',
'info_dict': { 'info_dict': {
'id': '2189178', 'id': '2189178',
'ext': 'flv', 'ext': 'mp4',
'title': 'Zeichentrick 1', 'title': 'Zeichentrick 1',
'age_limit': 18, 'age_limit': 18,
} }
@ -27,38 +22,18 @@ class YouJizzIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
# YouJizz's HTML5 player has invalid HTML
webpage = webpage.replace('"controls', '" controls')
age_limit = self._rta_search(webpage) age_limit = self._rta_search(webpage)
video_title = self._html_search_regex( video_title = self._html_search_regex(
r'<title>\s*(.*)\s*</title>', webpage, 'title') r'<title>\s*(.*)\s*</title>', webpage, 'title')
embed_page_url = self._search_regex( info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
r'(https?://www.youjizz.com/videos/embed/[0-9]+)',
webpage, 'embed page')
webpage = self._download_webpage(
embed_page_url, video_id, note='downloading embed page')
# Get the video URL info_dict.update({
m_playlist = re.search(r'so.addVariable\("playlist", ?"(?P<playlist>.+?)"\);', webpage)
if m_playlist is not None:
playlist_url = m_playlist.group('playlist')
playlist_page = self._download_webpage(playlist_url, video_id,
'Downloading playlist page')
m_levels = list(re.finditer(r'<level bitrate="(\d+?)" file="(.*?)"', playlist_page))
if len(m_levels) == 0:
raise ExtractorError('Unable to extract video url')
videos = [(int(m.group(1)), m.group(2)) for m in m_levels]
(_, video_url) = sorted(videos)[0]
video_url = video_url.replace('%252F', '%2F')
else:
video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
webpage, 'video URL')
return {
'id': video_id, 'id': video_id,
'url': video_url,
'title': video_title, 'title': video_title,
'ext': 'flv',
'format': 'flv',
'player_url': embed_page_url,
'age_limit': age_limit, 'age_limit': age_limit,
} })
return info_dict