X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdailymotion.py;h=4c0488245cd60df341df74110a434ed554fa304e;hb=57dd9a8f2f5885fb3d909c4905adb69b4749491c;hp=259806f385d621b909f465f0dc78271fb352c4fe;hpb=bd8e5c7ca286418e1e4162d7be6f3a30be581e87;p=youtube-dl.git diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 259806f38..4c0488245 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -10,6 +10,7 @@ from ..utils import ( compat_str, get_element_by_attribute, get_element_by_id, + orderedSet, ExtractorError, ) @@ -27,6 +28,15 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)' IE_NAME = u'dailymotion' + + _FORMATS = [ + (u'stream_h264_ld_url', u'ld'), + (u'stream_h264_url', u'standard'), + (u'stream_h264_hq_url', u'hq'), + (u'stream_h264_hd_url', u'hd'), + (u'stream_h264_hd1080_url', u'hd180'), + ] + _TESTS = [ { u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech', @@ -59,7 +69,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): video_id = mobj.group(1).split('_')[0].split('?')[0] - video_extension = 'mp4' url = 'http://www.dailymotion.com/video/%s' % video_id # Retrieve video webpage to extract further information @@ -98,18 +107,24 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title'] raise ExtractorError(msg, expected=True) - # TODO: support choosing qualities - - for key in ['stream_h264_hd1080_url','stream_h264_hd_url', - 'stream_h264_hq_url','stream_h264_url', - 'stream_h264_ld_url']: - if info.get(key):#key in info and info[key]: - max_quality = key - self.to_screen(u'Using %s' % key) - break - else: + formats = [] + for (key, format_id) in self._FORMATS: + video_url = info.get(key) + if video_url is not None: + m_size = re.search(r'H264-(\d+)x(\d+)', video_url) + if m_size is not None: + width, height = m_size.group(1), m_size.group(2) + else: + width, height = None, None + formats.append({ + 'url': video_url, + 'ext': 'mp4', + 'format_id': format_id, + 'width': width, + 'height': height, + }) + if not formats: raise ExtractorError(u'Unable to extract video URL') - video_url = info[max_quality] # subtitles video_subtitles = self.extract_subtitles(video_id) @@ -119,11 +134,10 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): return [{ 'id': video_id, - 'url': video_url, + 'formats': formats, 'uploader': video_uploader, 'upload_date': video_upload_date, 'title': self._og_search_title(webpage), - 'ext': video_extension, 'subtitles': video_subtitles, 'thumbnail': info['thumbnail_url'] }] @@ -158,12 +172,12 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): id, u'Downloading page %s' % pagenum) playlist_el = get_element_by_attribute(u'class', u'video_list', webpage) - video_ids.extend(re.findall(r'data-id="(.+?)" data-ext-id', playlist_el)) + video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el)) if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: break return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion') - for video_id in video_ids] + for video_id in orderedSet(video_ids)] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url)