X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=d71e1a90ee9b32cb1c4bc5a4cca5741a819edc64;hb=320e26a0af46dcefd53ba06656c986def933bc6b;hp=6a6545c9b578fba948962542d602bc5352b86840;hpb=71f37e90ef330f056abe456c93d59cee23765ede;p=youtube-dl

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 6a6545c9b..d71e1a90e 100755
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -152,6 +152,10 @@ class InfoExtractor(object):
         """Report information extraction."""
         self.to_screen(u'%s: Extracting information' % id_or_name)
 
+    def report_download_webpage(self, video_id):
+        """Report webpage download."""
+        self.to_screen(u'%s: Downloading webpage' % video_id)
+
     def report_age_confirmation(self):
         """Report attempt to confirm age."""
         self.to_screen(u'Confirming age')
@@ -570,7 +574,11 @@ class YoutubeIE(InfoExtractor):
         if video_description:
             video_description = clean_html(video_description)
         else:
-            video_description = ''
+            fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
+            if fd_mobj:
+                video_description = unescapeHTML(fd_mobj.group(1))
+            else:
+                video_description = u''
 
         # subtitles
         video_subtitles = None
@@ -687,10 +695,6 @@ class MetacafeIE(InfoExtractor):
         """Report disclaimer retrieval."""
         self.to_screen(u'Retrieving disclaimer')
 
-    def report_download_webpage(self, video_id):
-        """Report webpage download."""
-        self.to_screen(u'%s: Downloading webpage' % video_id)
-
     def _real_initialize(self):
         # Retrieve disclaimer
         request = compat_urllib_request.Request(self._DISCLAIMER)
@@ -878,10 +882,6 @@ class PhotobucketIE(InfoExtractor):
     def __init__(self, downloader=None):
         InfoExtractor.__init__(self, downloader)
 
-    def report_download_webpage(self, video_id):
-        """Report webpage download."""
-        self.to_screen(u'%s: Downloading webpage' % video_id)
-
     def _real_extract(self, url):
         # Extract id from URL
         mobj = re.match(self._VALID_URL, url)
@@ -943,10 +943,6 @@ class YahooIE(InfoExtractor):
     def __init__(self, downloader=None):
         InfoExtractor.__init__(self, downloader)
 
-    def report_download_webpage(self, video_id):
-        """Report webpage download."""
-        self.to_screen(u'%s: Downloading webpage' % video_id)
-
     def _real_extract(self, url, new_video=True):
         # Extract ID from URL
         mobj = re.match(self._VALID_URL, url)
@@ -1079,10 +1075,6 @@ class VimeoIE(InfoExtractor):
     def __init__(self, downloader=None):
         InfoExtractor.__init__(self, downloader)
 
-    def report_download_webpage(self, video_id):
-        """Report webpage download."""
-        self.to_screen(u'%s: Downloading webpage' % video_id)
-
     def _real_extract(self, url, new_video=True):
         # Extract ID from URL
         mobj = re.match(self._VALID_URL, url)
@@ -1196,10 +1188,6 @@ class ArteTvIE(InfoExtractor):
     def __init__(self, downloader=None):
         InfoExtractor.__init__(self, downloader)
 
-    def report_download_webpage(self, video_id):
-        """Report webpage download."""
-        self.to_screen(u'%s: Downloading webpage' % video_id)
-
     def fetch_webpage(self, url):
         request = compat_urllib_request.Request(url)
         try:
@@ -1224,7 +1212,7 @@ class ArteTvIE(InfoExtractor):
 
         for (i, key, err) in matchTuples:
             if mobj.group(i) is None:
-                self._downloader.trouble(err)
+                self._downloader.report_error(err)
                 return
             else:
                 info[key] = mobj.group(i)
@@ -1238,7 +1226,7 @@ class ArteTvIE(InfoExtractor):
             r'src="(.*?/videothek_js.*?\.js)',
             0,
             [
-                (1, 'url', u'ERROR: Invalid URL: %s' % url)
+                (1, 'url', u'Invalid URL: %s' % url)
             ]
         )
         http_host = url.split('/')[2]
@@ -1250,9 +1238,9 @@ class ArteTvIE(InfoExtractor):
                 '(rtmp://.*?)\'',
             re.DOTALL,
             [
-                (1, 'path',   u'ERROR: could not extract video path: %s' % url),
-                (2, 'player', u'ERROR: could not extract video player: %s' % url),
-                (3, 'url',    u'ERROR: could not extract video url: %s' % url)
+                (1, 'path',   u'could not extract video path: %s' % url),
+                (2, 'player', u'could not extract video player: %s' % url),
+                (3, 'url',    u'could not extract video url: %s' % url)
             ]
         )
         video_url = u'%s/%s' % (info.get('url'), info.get('path'))
@@ -1264,7 +1252,7 @@ class ArteTvIE(InfoExtractor):
             r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
             0,
             [
-                (1, 'url', u'ERROR: Invalid URL: %s' % url)
+                (1, 'url', u'Invalid URL: %s' % url)
             ]
         )
         next_url = compat_urllib_parse.unquote(info.get('url'))
@@ -1273,7 +1261,7 @@ class ArteTvIE(InfoExtractor):
             r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
             0,
             [
-                (1, 'url', u'ERROR: Could not find <video> tag: %s' % url)
+                (1, 'url', u'Could not find <video> tag: %s' % url)
             ]
         )
         next_url = compat_urllib_parse.unquote(info.get('url'))
@@ -1286,10 +1274,10 @@ class ArteTvIE(InfoExtractor):
                 '<url quality="hd">(.*?)</url>',
             re.DOTALL,
             [
-                (1, 'id',    u'ERROR: could not extract video id: %s' % url),
-                (2, 'title', u'ERROR: could not extract video title: %s' % url),
-                (3, 'date',  u'ERROR: could not extract video date: %s' % url),
-                (4, 'url',   u'ERROR: could not extract video url: %s' % url)
+                (1, 'id',    u'could not extract video id: %s' % url),
+                (2, 'title', u'could not extract video title: %s' % url),
+                (3, 'date',  u'could not extract video date: %s' % url),
+                (4, 'url',   u'could not extract video url: %s' % url)
             ]
         )
 
@@ -1518,7 +1506,7 @@ class YoutubeSearchIE(InfoExtractor):
             api_response = json.loads(data)['data']
 
             if not 'items' in api_response:
-                self._downloader.trouble(u'[youtube] No video results')
+                self._downloader.report_error(u'[youtube] No video results')
                 return
 
             new_ids = list(video['id'] for video in api_response['items'])
@@ -2016,10 +2004,6 @@ class DepositFilesIE(InfoExtractor):
 
     _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
 
-    def report_download_webpage(self, file_id):
-        """Report webpage download."""
-        self.to_screen(u'%s: Downloading webpage' % file_id)
-
     def _real_extract(self, url):
         file_id = url.split('/')[-1]
         # Rebuild url in english locale
@@ -2787,7 +2771,7 @@ class SoundcloudSetIE(InfoExtractor):
     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)
+            self._downloader.report_error(u'invalid URL: %s' % url)
             return
 
         # extract uploader (which is in the url)
@@ -2805,14 +2789,14 @@ class SoundcloudSetIE(InfoExtractor):
             info_json_bytes = compat_urllib_request.urlopen(request).read()
             info_json = info_json_bytes.decode('utf-8')
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
+            self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err))
             return
 
         videos = []
         info = json.loads(info_json)
         if 'errors' in info:
             for err in info['errors']:
-                self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err['error_message']))
+                self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err['error_message']))
             return
 
         for track in info['tracks']:
@@ -2825,7 +2809,7 @@ class SoundcloudSetIE(InfoExtractor):
                 stream_json_bytes = compat_urllib_request.urlopen(request).read()
                 stream_json = stream_json_bytes.decode('utf-8')
             except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                self._downloader.trouble(u'ERROR: unable to download stream definitions: %s' % compat_str(err))
+                self._downloader.report_error(u'unable to download stream definitions: %s' % compat_str(err))
                 return
 
             streams = json.loads(stream_json)
@@ -2857,7 +2841,7 @@ class InfoQIE(InfoExtractor):
         self.report_extraction(url)
 
         # Extract video URL
-        mobj = re.search(r"jsclassref='([^']*)'", webpage)
+        mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage)
         if mobj is None:
             self._downloader.report_error(u'unable to extract video url')
             return
@@ -3010,10 +2994,6 @@ class StanfordOpenClassroomIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
     IE_NAME = u'stanfordoc'
 
-    def report_download_webpage(self, objid):
-        """Report information extraction."""
-        self.to_screen(u'%s: Downloading webpage' % objid)
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:
@@ -3173,7 +3153,7 @@ class MTVIE(InfoExtractor):
             format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
             video_url = rendition.find('./src').text
         except KeyError:
-            self._downloader.trouble('Invalid rendition field.')
+            self._downloader.report_error('Invalid rendition field.')
             return
 
         info = {
@@ -3192,10 +3172,6 @@ class MTVIE(InfoExtractor):
 class YoukuIE(InfoExtractor):
     _VALID_URL =  r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
 
-    def report_download_webpage(self, file_id):
-        """Report webpage download."""
-        self.to_screen(u'%s: Downloading webpage' % file_id)
-
     def _gen_sid(self):
         nowTime = int(time.time() * 1000)
         random1 = random.randint(1000,1998)
@@ -3305,10 +3281,6 @@ class XNXXIE(InfoExtractor):
     VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
     VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&amp;'
 
-    def report_webpage(self, video_id):
-        """Report information extraction"""
-        self.to_screen(u'%s: Downloading webpage' % video_id)
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:
@@ -3316,7 +3288,7 @@ class XNXXIE(InfoExtractor):
             return
         video_id = mobj.group(1)
 
-        self.report_webpage(video_id)
+        self.report_download_webpage(video_id)
 
         # Get webpage content
         try:
@@ -3620,7 +3592,7 @@ class FunnyOrDieIE(InfoExtractor):
         if not m:
             m = re.search(r'<title>(?P<title>[^<]+?)</title>', webpage)
             if not m:
-                self._downloader.trouble(u'Cannot find video title')
+                self._downloader.report_error(u'Cannot find video title')
         title = clean_html(m.group('title'))
 
         m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
@@ -3726,7 +3698,7 @@ class WorldStarHipHopIE(InfoExtractor):
             else:
                 ext = 'flv'
         else:
-            self._downloader.trouble(u'ERROR: Cannot find video url for %s' % video_id)
+            self._downloader.report_error(u'Cannot find video url for %s' % video_id)
             return
 
         _title = r"""<title>(.*)</title>"""
@@ -4246,7 +4218,7 @@ class LiveLeakIE(InfoExtractor):
     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)
+            self._downloader.report_error(u'invalid URL: %s' % url)
             return
 
         video_id = mobj.group('video_id')
@@ -4261,7 +4233,7 @@ class LiveLeakIE(InfoExtractor):
 
         m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
         if not m:
-            self._downloader.trouble(u'Cannot find video title')
+            self._downloader.report_error(u'Cannot find video title')
         title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip()
 
         m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)