1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 20:48:04 +01:00
youtube-dl/youtube_dl/extractor/youjizz.py

62 lines
2.2 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-06-23 22:14:22 +02:00
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class YouJizzIE(InfoExtractor):
2014-11-12 15:19:23 +01:00
_VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/[^/#?]+-(?P<id>[0-9]+)\.html(?:$|[?#])'
2013-06-27 20:46:46 +02:00
_TEST = {
'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
'md5': '07e15fa469ba384c7693fd246905547c',
'info_dict': {
2014-11-12 15:19:23 +01:00
'id': '2189178',
'ext': 'flv',
"title": "Zeichentrick 1",
"age_limit": 18,
2013-06-27 20:46:46 +02:00
}
}
2013-06-23 22:14:22 +02:00
def _real_extract(self, url):
2014-11-12 15:19:23 +01:00
video_id = self._match_id(url)
2013-06-23 22:14:22 +02:00
webpage = self._download_webpage(url, video_id)
age_limit = self._rta_search(webpage)
2014-11-12 15:19:23 +01:00
video_title = self._html_search_regex(
r'<title>\s*(.*)\s*</title>', webpage, 'title')
embed_page_url = self._search_regex(
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')
2013-06-23 22:14:22 +02:00
# Get the video URL
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')
2013-06-23 22:14:22 +02:00
return {
'id': video_id,
'url': video_url,
'title': video_title,
'ext': 'flv',
'format': 'flv',
'player_url': embed_page_url,
'age_limit': age_limit,
}