X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fmtv.py;h=dd06395891ac02ce81b40efd471776cb080d328d;hb=a72df5f36feddaffbcfa35e3415562509a9f67b4;hp=e8bb527b89f443fb433694ac9e195fbbf5d2476e;hpb=c9c194053dfeb1b3b1a7a2cb29b1b9f34081ca5e;p=youtube-dl.git diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index e8bb527b8..dd0639589 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -4,18 +4,21 @@ import re from .common import InfoExtractor from ..compat import ( - compat_urllib_parse, + compat_urllib_parse_urlencode, compat_str, + compat_xpath, ) from ..utils import ( ExtractorError, find_xpath_attr, fix_xml_ampersands, + float_or_none, HEADRequest, sanitized_Request, unescapeHTML, url_basename, RegexNotFoundError, + xpath_text, ) @@ -82,9 +85,10 @@ class MTVServicesInfoExtractor(InfoExtractor): rtmp_video_url = rendition.find('./src').text if rtmp_video_url.endswith('siteunavail.png'): continue + new_url = self._transform_rtmp_url(rtmp_video_url) formats.append({ - 'ext': ext, - 'url': self._transform_rtmp_url(rtmp_video_url), + 'ext': 'flv' if new_url.startswith('rtmp') else ext, + 'url': new_url, 'format_id': rendition.get('bitrate'), 'width': int(rendition.get('width')), 'height': int(rendition.get('height')), @@ -110,7 +114,8 @@ class MTVServicesInfoExtractor(InfoExtractor): uri = itemdoc.find('guid').text video_id = self._id_from_uri(uri) self.report_extraction(video_id) - mediagen_url = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))).attrib['url'] + content_el = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))) + mediagen_url = content_el.attrib['url'] # Remove the templates, like &device={device} mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url) if 'acceptMethods' not in mediagen_url: @@ -128,11 +133,7 @@ class MTVServicesInfoExtractor(InfoExtractor): message += item.text raise ExtractorError(message, expected=True) - description_node = itemdoc.find('description') - if description_node is not None: - description = description_node.text.strip() - else: - description = None + description = xpath_text(itemdoc, 'description') title_el = None if title_el is None: @@ -140,9 +141,9 @@ class MTVServicesInfoExtractor(InfoExtractor): itemdoc, './/{http://search.yahoo.com/mrss/}category', 'scheme', 'urn:mtvn:video_title') if title_el is None: - title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title') + title_el = itemdoc.find(compat_xpath('.//{http://search.yahoo.com/mrss/}title')) if title_el is None: - title_el = itemdoc.find('.//title') or itemdoc.find('./title') + title_el = itemdoc.find(compat_xpath('.//title')) if title_el.text is None: title_el = None @@ -165,13 +166,14 @@ class MTVServicesInfoExtractor(InfoExtractor): 'id': video_id, 'thumbnail': self._get_thumbnail_url(uri, itemdoc), 'description': description, + 'duration': float_or_none(content_el.attrib.get('duration')), } def _get_feed_query(self, uri): data = {'uri': uri} if self._LANG: data['lang'] = self._LANG - return compat_urllib_parse.urlencode(data) + return compat_urllib_parse_urlencode(data) def _get_videos_info(self, uri): video_id = self._id_from_uri(uri)