aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/youjizz.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2013-06-23 22:14:22 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2013-06-23 22:14:22 +0200
commitc3c77cec300dd05938dcf175ab5fec536184589a (patch)
tree43a32b4445fbc465b10cd0f57a6f4e993d200896 /youtube_dl/extractor/youjizz.py
parent1183b85f50478f6e57e51d2af06e0f6730bb6cb1 (diff)
[youjizz] move into own file
Diffstat (limited to 'youtube_dl/extractor/youjizz.py')
-rw-r--r--youtube_dl/extractor/youjizz.py45
1 files changed, 45 insertions, 0 deletions
diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py
new file mode 100644
index 000000000..d9efac76e
--- /dev/null
+++ b/youtube_dl/extractor/youjizz.py
@@ -0,0 +1,45 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+)
+
+
+class YouJizzIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group('videoid')
+
+ # Get webpage content
+ webpage = self._download_webpage(url, video_id)
+
+ # Get the video title
+ video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
+ webpage, u'title').strip()
+
+ # Get the embed page
+ result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
+ if result is None:
+ raise ExtractorError(u'ERROR: unable to extract embed page')
+
+ embed_page_url = result.group(0).strip()
+ video_id = result.group('videoid')
+
+ webpage = self._download_webpage(embed_page_url, video_id)
+
+ # Get the video URL
+ video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
+ webpage, u'video URL')
+
+ info = {'id': video_id,
+ 'url': video_url,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'player_url': embed_page_url}
+
+ return [info]