working - worldstarhiphop IE

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 4b6a1c097e4977d8876acc4ebb3b864f93660b62..f69bad4f3a77d49be2d8b9cac3c6c256f4ee9898 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -2557,7 +2557,7 @@ class EscapistIE(InfoExtractor):
             'uploader': showName,
             'upload_date': None,
             'title': showName,
-            'ext': 'flv',
+            'ext': 'mp4',
             'thumbnail': imgUrl,
             'description': description,
             'player_url': playerUrl,
@@ -3591,55 +3591,6 @@ class FunnyOrDieIE(InfoExtractor):
         }
         return [info]
 
-class TweetReelIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?tweetreel\.com/[?](?P<id>[0-9a-z]+)$'
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
-            return
-
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-
-        m = re.search(r'<div id="left" status_id="([0-9]+)">', webpage)
-        if not m:
-            self._downloader.trouble(u'ERROR: Cannot find status ID')
-        status_id = m.group(1)
-
-        m = re.search(r'<div class="tweet_text">(.*?)</div>', webpage, flags=re.DOTALL)
-        if not m:
-            self._downloader.trouble(u'WARNING: Cannot find description')
-        desc = unescapeHTML(re.sub('<a.*?</a>', '', m.group(1))).strip()
-
-        m = re.search(r'<div class="tweet_info">.*?from <a target="_blank" href="https?://twitter.com/(?P<uploader_id>.+?)">(?P<uploader>.+?)</a>', webpage, flags=re.DOTALL)
-        if not m:
-            self._downloader.trouble(u'ERROR: Cannot find uploader')
-        uploader = unescapeHTML(m.group('uploader'))
-        uploader_id = unescapeHTML(m.group('uploader_id'))
-
-        m = re.search(r'<span unixtime="([0-9]+)"', webpage)
-        if not m:
-            self._downloader.trouble(u'ERROR: Cannot find upload date')
-        upload_date = datetime.datetime.fromtimestamp(int(m.group(1))).strftime('%Y%m%d')
-
-        title = desc
-        video_url = 'http://files.tweetreel.com/video/' + status_id + '.mov'
-
-        info = {
-            'id': video_id,
-            'url': video_url,
-            'ext': 'mov',
-            'title': title,
-            'description': desc,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
-            'internal_id': status_id,
-            'upload_date': upload_date
-        }
-        return [info]
-
 class SteamIE(InfoExtractor):
     _VALID_URL = r"""http://store.steampowered.com/
                 (?P<urltype>video|app)/ #If the page is only for videos or for a game
@@ -3703,6 +3654,62 @@ class UstreamIE(InfoExtractor):
                   }
         return [info]
 
+class WorldStarHipHopIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
+    IE_NAME = u'WorldStarHipHop'
+
+    def _real_extract(self, url):
+        _src_url = r"""(http://hw-videos.*(?:mp4|flv))"""
+
+        webpage_src = compat_urllib_request.urlopen(str(url)).read()
+        webpage_src = webpage_src.decode('utf-8')
+
+        mobj = re.search(_src_url, webpage_src)
+
+        if mobj is not None:
+            video_url = mobj.group()
+            if 'mp4' in video_url:
+                ext = 'mp4'
+            else:
+                ext = 'flv'
+        else:
+            video_url = None
+            ext = None
+
+        _title = r"""<title>(.*)</title>"""
+
+        mobj = re.search(_title, webpage_src)
+        
+        if mobj is not None:
+            title = mobj.group(1)
+        else:
+            title = 'World Start Hip Hop - %s' % time.ctime()
+
+        _thumbnail = r"""rel="image_src" href="(.*)" />"""
+        mobj = re.search(_thumbnail, webpage_src)
+
+        # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
+        if mobj is not None:
+            thumbnail = mobj.group(1)
+        else:
+            _title = r"""candytitles.*>(.*)</span>"""
+            mobj = re.search(_title, webpage_src)
+            if mobj is not None:
+                title = mobj.group(1)
+            thumbnail = None
+
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+        
+        results = [{
+                    'id': video_id,
+                    'url' : video_url,
+                    'title' : title,
+                    'thumbnail' : thumbnail,
+                    'ext' : ext,
+                    }]
+        return results
+
 class RBMARadioIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
 
@@ -4182,9 +4189,9 @@ def gen_extractors():
         GooglePlusIE(),
         ArteTvIE(),
         NBAIE(),
+        WorldStarHipHopIE(),
         JustinTVIE(),
         FunnyOrDieIE(),
-        TweetReelIE(),
         SteamIE(),
         UstreamIE(),
         RBMARadioIE(),