projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
[minhateca] Fix duration parsing
[youtube-dl]
/
youtube_dl
/
extractor
/
xvideos.py
diff --git
a/youtube_dl/extractor/xvideos.py
b/youtube_dl/extractor/xvideos.py
index 8b3cb3930d77c0c7a649a57afee84c2425713ba5..7e00448246beb9ab9b7c25f33b05e6f4f1bb8283 100644
(file)
--- a/
youtube_dl/extractor/xvideos.py
+++ b/
youtube_dl/extractor/xvideos.py
@@
-1,13
+1,27
@@
+from __future__ import unicode_literals
+
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
+ ExtractorError,
+ clean_html,
)
class XVideosIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
)
class XVideosIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
+ _TEST = {
+ 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
+ 'md5': '4b46ae6ea5e6e9086e714d883313c0c9',
+ 'info_dict': {
+ 'id': '4588838',
+ 'ext': 'flv',
+ 'title': 'Biker Takes his Girl',
+ 'age_limit': 18,
+ }
+ }
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@@
-17,19
+31,23
@@
class XVideosIE(InfoExtractor):
self.report_extraction(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
# Extract video URL
- video_url = compat_urllib_parse.unquote(
self._search_regex(r'flv_url=(.+?)&',
-
webpage, u
'video URL'))
+ video_url = compat_urllib_parse.unquote(
+
self._search_regex(r'flv_url=(.+?)&', webpage,
'video URL'))
# Extract title
# Extract title
- video_title = self._html_search_regex(
r'<title>(.*?)\s+-\s+XVID',
-
webpage, u
'title')
+ video_title = self._html_search_regex(
+
r'<title>(.*?)\s+-\s+XVID', webpage,
'title')
# Extract video thumbnail
# Extract video thumbnail
- video_thumbnail = self._search_regex(
r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)',
-
webpage, u
'thumbnail', fatal=False)
+ video_thumbnail = self._search_regex(
+
r'url_bigthumb=(.+?)&', webpage,
'thumbnail', fatal=False)
-
info =
{
+
return
{
'id': video_id,
'url': video_url,
'uploader': None,
'id': video_id,
'url': video_url,
'uploader': None,
@@
-38,6
+56,5
@@
class XVideosIE(InfoExtractor):
'ext': 'flv',
'thumbnail': video_thumbnail,
'description': None,
'ext': 'flv',
'thumbnail': video_thumbnail,
'description': None,
+ 'age_limit': 18,
}
}
-
- return [info]