]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/xtube.py
Merge tag 'upstream/2016.02.22'
[youtubedl] / youtube_dl / extractor / xtube.py
index 03ad88bededd60a7d8462bb85e5a8cb23db381b2..4075b8a4f8a705cf29aa1430656146350a8d07aa 100644 (file)
-import os
+from __future__ import unicode_literals
+
+import itertools
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
-    compat_urllib_parse_urlparse,
-    compat_urllib_request,
-    compat_urllib_parse,
+    int_or_none,
+    orderedSet,
+    sanitized_Request,
+    str_to_int,
 )
 
+
 class XTubeIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))'
-    _TEST = {
-        u'url': u'http://www.xtube.com/watch.php?v=kVTUy_G222_',
-        u'file': u'kVTUy_G222_.mp4',
-        u'md5': u'092fbdd3cbe292c920ef6fc6a8a9cdab',
-        u'info_dict': {
-            u"title": u"strange erotica",
-            u"description": u"surreal gay themed erotica...almost an ET kind of thing",
-            u"uploader": u"greenshowers",
-            u"age_limit": 18,
+    _VALID_URL = r'(?:xtube:|https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?P<display_id>[^/]+)-))(?P<id>[^/?&#]+)'
+
+    _TESTS = [{
+        # old URL schema
+        'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
+        'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
+        'info_dict': {
+            'id': 'kVTUy_G222_',
+            'ext': 'mp4',
+            'title': 'strange erotica',
+            'description': 'contains:an ET kind of thing',
+            'uploader': 'greenshowers',
+            'duration': 450,
+            'age_limit': 18,
         }
-    }
+    }, {
+        # new URL schema
+        'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
+        'only_matching': True,
+    }, {
+        'url': 'xtube:625837',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
-        url = 'http://www.' + mobj.group('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'<div class="p_5px[^>]*>([^<]+)', webpage, u'title')
-        video_uploader = self._html_search_regex(r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, u'uploader', fatal=False)
-        video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, u'description', default=None)
-        video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, u'video_url').replace('\\/', '/')
-        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)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        if not display_id:
+            display_id = video_id
+            url = 'http://www.xtube.com/watch.php?v=%s' % video_id
+
+        req = sanitized_Request(url)
+        req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1')
+        webpage = self._download_webpage(req, display_id)
+
+        flashvars = self._parse_json(
+            self._search_regex(
+                r'xt\.playerOps\s*=\s*({.+?});', webpage, 'player ops'),
+            video_id)['flashvars']
+
+        title = flashvars.get('title') or self._search_regex(
+            r'<h1>([^<]+)</h1>', webpage, 'title')
+        video_url = compat_urllib_parse_unquote(flashvars['video_url'])
+        duration = int_or_none(flashvars.get('video_duration'))
+
+        uploader = self._search_regex(
+            r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
+            webpage, 'uploader', fatal=False)
+        description = self._search_regex(
+            r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
+        view_count = str_to_int(self._search_regex(
+            r'<dt>Views:</dt>\s*<dd>([\d,\.]+)</dd>',
+            webpage, 'view count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            r'>Comments? \(([\d,\.]+)\)<',
+            webpage, 'comment count', fatal=False))
 
         return {
             'id': video_id,
-            'title': video_title,
-            'uploader': video_uploader,
-            'description': video_description,
+            'display_id': display_id,
             'url': video_url,
-            'ext': extension,
-            'format': format,
-            'format_id': format,
+            'title': title,
+            'description': description,
+            'uploader': uploader,
+            'duration': duration,
+            'view_count': view_count,
+            'comment_count': comment_count,
             'age_limit': 18,
         }
+
+
+class XTubeUserIE(InfoExtractor):
+    IE_DESC = 'XTube user profile'
+    _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
+    _TEST = {
+        'url': 'http://www.xtube.com/profile/greenshowers-4056496',
+        'info_dict': {
+            'id': 'greenshowers-4056496',
+            'age_limit': 18,
+        },
+        'playlist_mincount': 155,
+    }
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+
+        entries = []
+        for pagenum in itertools.count(1):
+            request = sanitized_Request(
+                'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
+                headers={
+                    'Cookie': 'popunder=4',
+                    'X-Requested-With': 'XMLHttpRequest',
+                    'Referer': url,
+                })
+
+            page = self._download_json(
+                request, user_id, 'Downloading videos JSON page %d' % pagenum)
+
+            html = page.get('html')
+            if not html:
+                break
+
+            for video_id in orderedSet([video_id for _, video_id in re.findall(
+                    r'data-plid=(["\'])(.+?)\1', html)]):
+                entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
+
+            page_count = int_or_none(page.get('pageCount'))
+            if not page_count or pagenum == page_count:
+                break
+
+        playlist = self.playlist_result(entries, user_id)
+        playlist['age_limit'] = 18
+        return playlist