[thvideo] Add support for playlists

[youtube-dl] / youtube_dl / extractor / thvideo.py

diff --git a/youtube_dl/extractor/thvideo.py b/youtube_dl/extractor/thvideo.py
index 9fa14d3c4c3462eb10fbda5f710e2b9befe31ea5..0ae20ea30bc307e014f63bc31c1288945b9a4046 100644 (file)
--- a/youtube_dl/extractor/thvideo.py
+++ b/youtube_dl/extractor/thvideo.py
@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class THVideoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?thvideo\.tv/v/th(?P<id>[0-9]+)'
+    _VALID_URL = r'http://(?:www\.)?thvideo\.tv/(?:v/th|mobile\.php\?cid=)(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://thvideo.tv/v/th1987/',
         'md5': 'fa107b1f73817e325e9433505a70db50',
@@ -30,18 +30,22 @@ class THVideoIE(InfoExtractor):
         video_id = mobj.group('id')
 
         # extract download link from mobile player page
-        webpage_player = self._download_webpage('http://thvideo.tv/mobile.php?cid=%s-0' % video_id, video_id)
-        video_url = self._html_search_regex(r'<source src="(.*?)" type', webpage_player, 'video url')
+        webpage_player = self._download_webpage(
+            'http://thvideo.tv/mobile.php?cid=%s-0' % (video_id),
+            video_id, note='Downloading video source page')
+        video_url = self._html_search_regex(
+            r'<source src="(.*?)" type', webpage_player, 'video url')
 
         # extract video info from main page
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'http://thvideo.tv/v/th%s' % (video_id), video_id)
         title = self._og_search_title(webpage)
         display_id = 'th%s' % video_id
         thumbnail = self._og_search_thumbnail(webpage)
         description = self._og_search_description(webpage)
-        upload_date_raw = self._html_search_regex(r'span itemprop="datePublished" content="(.*?)">', webpage,
-                                                  'upload date', fatal=False)
-        upload_date = unified_strdate(upload_date_raw)
+        upload_date = unified_strdate(self._html_search_regex(
+            r'span itemprop="datePublished" content="(.*?)">', webpage,
+            'upload date', fatal=False))
 
         return {
             'id': video_id,
@@ -52,4 +56,28 @@ class THVideoIE(InfoExtractor):
             'thumbnail': thumbnail,
             'description': description,
             'upload_date': upload_date
-        }
\ No newline at end of file
+        }
+
+
+class THVideoPlaylistIE(InfoExtractor):
+    _VALID_URL = r'http?://(?:www\.)?thvideo\.tv/mylist(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://thvideo.tv/mylist2',
+        'info_dict': {
+            'id': '2',
+            'title': '幻想万華鏡',
+        },
+        'playlist_mincount': 23,
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, 'playlist')
+        mobj = re.match(self._VALID_URL, url)
+        list_id = mobj.group('id')
+        list_title = self._html_search_regex(r'<h1 class="show_title">(.*?)<b id', webpage, 'playlist title')
+
+        entries = [
+            self.url_result('http://thvideo.tv/v/th' + id, 'THVideo')
+            for id in re.findall(r'<dd><a href="http://thvideo.tv/v/th(\d+)/" target=', webpage)]
+
+        return self.playlist_result(entries, list_id, list_title)
\ No newline at end of file