projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
FFmpegMergerPP: use the new system for specifying which files can be delete
[youtube-dl]
/
youtube_dl
/
extractor
/
xvideos.py
diff --git
a/youtube_dl/extractor/xvideos.py
b/youtube_dl/extractor/xvideos.py
index 85e99e1b02b8ab7e7647d6c91dbad08f4827d5f3..2a45dc574263f7e651020e591fcc40bdf987367d 100644
(file)
--- a/
youtube_dl/extractor/xvideos.py
+++ b/
youtube_dl/extractor/xvideos.py
@@
-3,51
+3,48
@@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
import re
from .common import InfoExtractor
-from ..
utils
import (
+from ..
compat
import (
compat_urllib_parse,
)
compat_urllib_parse,
)
+from ..utils import (
+ clean_html,
+ ExtractorError,
+)
class XVideosIE(InfoExtractor):
class XVideosIE(InfoExtractor):
- _VALID_URL = r'
^(?:https?://)?(?:www\.)?xvideos\.com/video(
[0-9]+)(?:.*)'
+ _VALID_URL = r'
https?://(?:www\.)?xvideos\.com/video(?P<id>
[0-9]+)(?:.*)'
_TEST = {
_TEST = {
- 'url': 'http://www.xvideos.com/video939581/funny_porns_by_s_-1',
- 'file': '939581.flv',
- 'md5': '1d0c835822f0a71a7bf011855db929d0',
+ 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
+ 'md5': '4b46ae6ea5e6e9086e714d883313c0c9',
'info_dict': {
'info_dict': {
- "title": "Funny Porns By >>>>S<<<<<< -1",
- "age_limit": 18,
+ 'id': '4588838',
+ 'ext': 'flv',
+ 'title': 'Biker Takes his Girl',
+ 'age_limit': 18,
}
}
def _real_extract(self, url):
}
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group(1)
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage = self._download_webpage(url, video_id)
- self.report_extraction(video_id)
+ mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
+ if mobj:
+ raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
- # Extract video URL
video_url = compat_urllib_parse.unquote(
self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
video_url = compat_urllib_parse.unquote(
self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
-
- # Extract title
video_title = self._html_search_regex(
r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
video_title = self._html_search_regex(
r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
-
- # Extract video thumbnail
video_thumbnail = self._search_regex(
r'url_bigthumb=(.+?)&', webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'url': video_url,
video_thumbnail = self._search_regex(
r'url_bigthumb=(.+?)&', webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'url': video_url,
- 'uploader': None,
- 'upload_date': None,
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,
- 'description': None,
'age_limit': 18,
}
'age_limit': 18,
}