added one-step realese script 'make release version=nn' - closes #158

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index ee8783ffd6bd3ad5ce72f4c93216e25f415ea07b..0835c447c1cf6955f17d246a461948be25bfa3fd 100644 (file)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -181,8 +181,8 @@ class YoutubeIE(InfoExtractor):
                        start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
                        end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
                        caption = unescapeHTML(caption)
-                       caption = unescapeHTML(caption) # double cycle, inentional
-                       srt += str(n) + '\n'
+                       caption = unescapeHTML(caption) # double cycle, intentional
+                       srt += str(n+1) + '\n'
                        srt += start + ' --> ' + end + '\n'
                        srt += caption + '\n\n'
                return srt
@@ -311,6 +311,11 @@ class YoutubeIE(InfoExtractor):
                                self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
                        return
 
+               # Check for "rental" videos
+               if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
+                       self._downloader.trouble(u'ERROR: "rental" videos not supported')
+                       return
+
                # Start extracting information
                self.report_information_extraction(video_id)
 
@@ -361,7 +366,8 @@ class YoutubeIE(InfoExtractor):
                                        srt_list = urllib2.urlopen(request).read()
                                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                                        raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
-                               srt_lang_list = re.findall(r'lang_code="([\w\-]+)"', srt_list)
+                               srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
+                               srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
                                if not srt_lang_list:
                                        raise Trouble(u'WARNING: video has no closed captions')
                                if self._downloader.params.get('subtitleslang', False):
@@ -369,14 +375,16 @@ class YoutubeIE(InfoExtractor):
                                elif 'en' in srt_lang_list:
                                        srt_lang = 'en'
                                else:
-                                       srt_lang = srt_lang_list[0]
+                                       srt_lang = srt_lang_list.keys()[0]
                                if not srt_lang in srt_lang_list:
                                        raise Trouble(u'WARNING: no closed captions found in the specified language')
-                               request = urllib2.Request('http://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id))
+                               request = urllib2.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id))
                                try:
                                        srt_xml = urllib2.urlopen(request).read()
                                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                                        raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
+                               if not srt_xml:
+                                       raise Trouble(u'WARNING: unable to download video subtitles')
                                video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8'))
                        except Trouble as trouble:
                                self._downloader.trouble(trouble[0])
@@ -1227,7 +1235,7 @@ class YoutubeSearchIE(InfoExtractor):
                InfoExtractor.__init__(self, downloader)
 
        def report_download_page(self, query, pagenum):
-               """Report attempt to download playlist page with given number."""
+               """Report attempt to download search page with given number."""
                query = query.decode(preferredencoding())
                self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
 
@@ -1463,8 +1471,8 @@ class YoutubePlaylistIE(InfoExtractor):
 
        _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
        _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
-       _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=PL%s&'
-       _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
+       _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&amp;list=(PL)?%s&'
+       _MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
        IE_NAME = u'youtube:playlist'
 
        def __init__(self, downloader=None):
@@ -2188,7 +2196,10 @@ class EscapistIE(InfoExtractor):
 
                self.report_extraction(showName)
                try:
-                       webPage = urllib2.urlopen(url).read()
+                       webPage = urllib2.urlopen(url)
+                       webPageBytes = webPage.read()
+                       m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
+                       webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
                        return
@@ -2351,11 +2362,11 @@ class XVideosIE(InfoExtractor):
 
 
                # Extract video thumbnail
-               mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
+               mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
                        return
-               video_thumbnail = mobj.group(1).decode('utf-8')
+               video_thumbnail = mobj.group(0).decode('utf-8')
 
                info = {
                        'id': video_id,
@@ -2449,7 +2460,7 @@ class SoundcloudIE(InfoExtractor):
                        try:
                                upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
                        except Exception, e:
-                               print str(e)
+                               self._downloader.to_stderr(str(e))
 
                # for soundcloud, a request to a cross domain is required for cookies
                request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)