kumi/yt-dlp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[youjizz] Simplify and use unicode_literals

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-01-29 16:44:21 +01:00
parent 245b612a36
commit 0b76600deb
1 changed files with 22 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
youtube_dl/extractor/youjizz.py
View file

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -9,12 +11,12 @@ from ..utils import (
class YouJizzIE(InfoExtractor): class YouJizzIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$' _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
_TEST = { _TEST = {
u'url': u'http://www.youjizz.com/videos/zeichentrick-1-2189178.html', 'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
u'file': u'2189178.flv', 'file': '2189178.flv',
u'md5': u'07e15fa469ba384c7693fd246905547c', 'md5': '07e15fa469ba384c7693fd246905547c',
u'info_dict': { 'info_dict': {
u"title": u"Zeichentrick 1", "title": "Zeichentrick 1",
u"age_limit": 18, "age_limit": 18,
} }
} }
@ -30,12 +32,12 @@ class YouJizzIE(InfoExtractor):
# Get the video title # Get the video title
video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>', video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
webpage, u'title').strip() webpage, 'title').strip()
# Get the embed page # Get the embed page
result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage) result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
if result is None: if result is None:
raise ExtractorError(u'ERROR: unable to extract embed page') raise ExtractorError('ERROR: unable to extract embed page')
embed_page_url = result.group(0).strip() embed_page_url = result.group(0).strip()
video_id = result.group('videoid') video_id = result.group('videoid')
@ -47,23 +49,23 @@ class YouJizzIE(InfoExtractor):
if m_playlist is not None: if m_playlist is not None:
playlist_url = m_playlist.group('playlist') playlist_url = m_playlist.group('playlist')
playlist_page = self._download_webpage(playlist_url, video_id, playlist_page = self._download_webpage(playlist_url, video_id,
u'Downloading playlist page') 'Downloading playlist page')
m_levels = list(re.finditer(r'<level bitrate="(\d+?)" file="(.*?)"', playlist_page)) m_levels = list(re.finditer(r'<level bitrate="(\d+?)" file="(.*?)"', playlist_page))
if len(m_levels) == 0: if len(m_levels) == 0:
raise ExtractorError(u'Unable to extract video url') raise ExtractorError('Unable to extract video url')
videos = [(int(m.group(1)), m.group(2)) for m in m_levels] videos = [(int(m.group(1)), m.group(2)) for m in m_levels]
(_, video_url) = sorted(videos)[0] (_, video_url) = sorted(videos)[0]
video_url = video_url.replace('%252F', '%2F') video_url = video_url.replace('%252F', '%2F')
else: else:
video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
webpage, u'video URL') webpage, 'video URL')
info = {'id': video_id, return {
'url': video_url, 'id': video_id,
'title': video_title, 'url': video_url,
'ext': 'flv', 'title': video_title,
'format': 'flv', 'ext': 'flv',
'player_url': embed_page_url, 'format': 'flv',
'age_limit': age_limit} 'player_url': embed_page_url,
'age_limit': age_limit,
return [info] }