X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Fxtube.py;h=1644f53c876329f053406be3d3dc1aa463cddc1b;hb=d2a9de78dfc629aaaaf8a2a30432d5f02c949e9a;hp=273d93d9ee544b74f22daa20a195b8e4bc7b05a2;hpb=22a6f15061127045f4d6ae1ff4efc922fa372cc2;p=youtube-dl.git
diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py
index 273d93d9e..1644f53c8 100644
--- a/youtube_dl/extractor/xtube.py
+++ b/youtube_dl/extractor/xtube.py
@@ -1,18 +1,20 @@
from __future__ import unicode_literals
import re
-import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_request,
+ compat_urllib_parse,
+)
+from ..utils import (
parse_duration,
str_to_int,
)
class XTubeIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?(?Pxtube\.com/watch\.php\?v=(?P[^/?&]+))'
+ _VALID_URL = r'https?://(?:www\.)?(?Pxtube\.com/watch\.php\?v=(?P[^/?]+))'
_TEST = {
'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
@@ -20,7 +22,7 @@ class XTubeIE(InfoExtractor):
'id': 'kVTUy_G222_',
'ext': 'mp4',
'title': 'strange erotica',
- 'description': 'surreal gay themed erotica...almost an ET kind of thing',
+ 'description': 'contains:an ET kind of thing',
'uploader': 'greenshowers',
'duration': 450,
'age_limit': 18,
@@ -28,41 +30,49 @@ class XTubeIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
- url = 'http://www.' + mobj.group('url')
+ video_id = self._match_id(url)
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
- video_title = self._html_search_regex(r'([^<]+)', webpage, 'title')
+ video_title = self._html_search_regex(
+ r'
([^<]+)', webpage, 'title')
video_uploader = self._html_search_regex(
- r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, 'uploader', fatal=False)
+ [r"var\s+contentOwnerId\s*=\s*'([^']+)",
+ r'By:\s*([^<]+)', webpage, 'description', fatal=False)
+ r'([^<]+)',
+ webpage, 'description', fatal=False)
duration = parse_duration(self._html_search_regex(
- r'Runtime: ([^<]+)
', webpage, 'duration', fatal=False))
- view_count = self._html_search_regex(
- r'Views: ([\d,\.]+)
', webpage, 'view count', fatal=False)
- if view_count:
- view_count = str_to_int(view_count)
- comment_count = self._html_search_regex(
- r'', webpage, 'comment count', fatal=False)
- if comment_count:
- comment_count = str_to_int(comment_count)
-
- player_quality_option = json.loads(self._html_search_regex(
- r'playerQualityOption = ({.+?});', webpage, 'player quality option'))
-
- QUALITIES = ['3gp', 'mp4_normal', 'mp4_high', 'flv', 'mp4_ultra', 'mp4_720', 'mp4_1080']
- formats = [
- {
- 'url': furl,
+ r'Runtime: ([^<]+)
',
+ webpage, 'duration', fatal=False))
+ view_count = str_to_int(self._html_search_regex(
+ r'Views: ([\d,\.]+)',
+ webpage, 'view count', fatal=False))
+ comment_count = str_to_int(self._html_search_regex(
+ r'',
+ webpage, 'comment count', fatal=False))
+
+ formats = []
+ for format_id, video_url in re.findall(
+ r'flashvars\.quality_(.+?)\s*=\s*"([^"]+)"', webpage):
+ fmt = {
+ 'url': compat_urllib_parse.unquote(video_url),
'format_id': format_id,
- 'preference': QUALITIES.index(format_id) if format_id in QUALITIES else -1,
- } for format_id, furl in player_quality_option.items()
- ]
+ }
+ m = re.search(r'^(?P\d+)[pP]', format_id)
+ if m:
+ fmt['height'] = int(m.group('height'))
+ formats.append(fmt)
+
+ if not formats:
+ video_url = compat_urllib_parse.unquote(self._search_regex(
+ r'flashvars\.video_url\s*=\s*"([^"]+)"',
+ webpage, 'video URL'))
+ formats.append({'url': video_url})
+
self._sort_formats(formats)
return {
@@ -85,6 +95,7 @@ class XTubeUserIE(InfoExtractor):
'url': 'http://www.xtube.com/community/profile.php?user=greenshowers',
'info_dict': {
'id': 'greenshowers',
+ 'age_limit': 18,
},
'playlist_mincount': 155,
}
@@ -97,7 +108,7 @@ class XTubeUserIE(InfoExtractor):
url, username, note='Retrieving profile page')
video_count = int(self._search_regex(
- r'%s\'s Videos \(([0-9]+)\)'%username, profile_page,
+ r'%s\'s Videos \(([0-9]+)\)' % username, profile_page,
'video count'))
PAGE_SIZE = 25
@@ -114,6 +125,7 @@ class XTubeUserIE(InfoExtractor):
return {
'_type': 'playlist',
'id': username,
+ 'age_limit': 18,
'entries': [{
'_type': 'url',
'url': eurl,