X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fxtube.py;h=a1fe24050003273f736d605fa662318e4dc6e17d;hb=9f0ee2a3883ec6f6fdccba90085cb925aaa2f617;hp=d3eefd086720a82aa5f78c52d941fc6aee35c655;hpb=f55a1f0a8815c89b01a7a353cfa0bd5118f75829;p=youtube-dl
diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py
index d3eefd086..a1fe24050 100644
--- a/youtube_dl/extractor/xtube.py
+++ b/youtube_dl/extractor/xtube.py
@@ -1,19 +1,18 @@
from __future__ import unicode_literals
-import os
import re
from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
from ..utils import (
- compat_urllib_parse_urlparse,
- compat_urllib_request,
parse_duration,
+ sanitized_Request,
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',
@@ -21,7 +20,7 @@ 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,
@@ -29,37 +28,50 @@ 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 = sanitized_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)
- video_url = self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, 'video_url').replace('\\/', '/')
+ 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)
-
- path = compat_urllib_parse_urlparse(video_url).path
- extension = os.path.splitext(path)[1][1:]
- format = path.split('/')[5].split('_')[:2]
- format[0] += 'p'
- format[1] += 'k'
- format = "-".join(format)
+ 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,
+ }
+ 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 {
'id': video_id,
@@ -69,9 +81,52 @@ class XTubeIE(InfoExtractor):
'duration': duration,
'view_count': view_count,
'comment_count': comment_count,
- 'url': video_url,
- 'ext': extension,
- 'format': format,
- 'format_id': format,
+ 'formats': formats,
+ 'age_limit': 18,
+ }
+
+
+class XTubeUserIE(InfoExtractor):
+ IE_DESC = 'XTube user profile'
+ _VALID_URL = r'https?://(?:www\.)?xtube\.com/community/profile\.php\?(.*?)user=(?P[^]+)(?:$|[])'
+ _TEST = {
+ 'url': 'http://www.xtube.com/community/profile.php?user=greenshowers',
+ 'info_dict': {
+ 'id': 'greenshowers',
+ 'age_limit': 18,
+ },
+ 'playlist_mincount': 155,
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ username = mobj.group('username')
+
+ profile_page = self._download_webpage(
+ url, username, note='Retrieving profile page')
+
+ video_count = int(self._search_regex(
+ r'%s\'s Videos \(([0-9]+)\)' % username, profile_page,
+ 'video count'))
+
+ PAGE_SIZE = 25
+ urls = []
+ page_count = (video_count + PAGE_SIZE + 1) // PAGE_SIZE
+ for n in range(1, page_count + 1):
+ lpage_url = 'http://www.xtube.com/user_videos.php?page=%d&u=%s' % (n, username)
+ lpage = self._download_webpage(
+ lpage_url, username,
+ note='Downloading page %d/%d' % (n, page_count))
+ urls.extend(
+ re.findall(r'addthis:url="([^"]+)"', lpage))
+
+ return {
+ '_type': 'playlist',
+ 'id': username,
'age_limit': 18,
+ 'entries': [{
+ '_type': 'url',
+ 'url': eurl,
+ 'ie_key': 'XTube',
+ } for eurl in urls]
}