diff options
| -rw-r--r-- | youtube_dl/extractor/gamespot.py | 71 | ||||
| -rw-r--r-- | youtube_dl/extractor/tudou.py | 36 | ||||
| -rw-r--r-- | youtube_dl/extractor/youku.py | 2 |
3 files changed, 63 insertions, 46 deletions
diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 5edbf678a..098768361 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -1,56 +1,59 @@ import re -import xml.etree.ElementTree +import json from .common import InfoExtractor from ..utils import ( - unified_strdate, compat_urllib_parse, + compat_urlparse, + unescapeHTML, + get_meta_content, ) + class GameSpotIE(InfoExtractor): - _WORKING = False _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?' _TEST = { u"url": u"http://www.gamespot.com/arma-iii/videos/arma-iii-community-guide-sitrep-i-6410818/", - u"file": u"6410818.mp4", + u"file": u"gs-2300-6410818.mp4", u"md5": u"b2a30deaa8654fcccd43713a6b6a4825", u"info_dict": { u"title": u"Arma 3 - Community Guide: SITREP I", - u"upload_date": u"20130627", + u'description': u'Check out this video where some of the basics of Arma 3 is explained.', } } - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('page_id') + page_id = video_id = mobj.group('page_id') webpage = self._download_webpage(url, page_id) - video_id = self._html_search_regex([r'"og:video" content=".*?\?id=(\d+)"', - r'http://www\.gamespot\.com/videoembed/(\d+)'], - webpage, 'video id') - data = compat_urllib_parse.urlencode({'id': video_id, 'newplayer': '1'}) - info_url = 'http://www.gamespot.com/pages/video_player/xml.php?' + data - info_xml = self._download_webpage(info_url, video_id) - doc = xml.etree.ElementTree.fromstring(info_xml) - clip_el = doc.find('./playList/clip') + data_video_json = self._search_regex(r'data-video=\'(.*?)\'', webpage, u'data video') + data_video = json.loads(unescapeHTML(data_video_json)) - http_urls = [{'url': node.find('filePath').text, - 'rate': int(node.find('rate').text)} - for node in clip_el.find('./httpURI')] - best_quality = sorted(http_urls, key=lambda f: f['rate'])[-1] - video_url = best_quality['url'] - title = clip_el.find('./title').text - ext = video_url.rpartition('.')[2] - thumbnail_url = clip_el.find('./screenGrabURI').text - view_count = int(clip_el.find('./views').text) - upload_date = unified_strdate(clip_el.find('./postDate').text) + # Transform the manifest url to a link to the mp4 files + # they are used in mobile devices. + f4m_url = data_video['videoStreams']['f4m_stream'] + f4m_path = compat_urlparse.urlparse(f4m_url).path + QUALITIES_RE = r'((,\d+)+,?)' + qualities = self._search_regex(QUALITIES_RE, f4m_path, u'qualities').strip(',').split(',') + http_path = f4m_path[1:].split('/', 1)[1] + http_template = re.sub(QUALITIES_RE, r'%s', http_path) + http_template = http_template.replace('.csmil/manifest.f4m', '') + http_template = compat_urlparse.urljoin('http://video.gamespotcdn.com/', http_template) + formats = [] + for q in qualities: + formats.append({ + 'url': http_template % q, + 'ext': 'mp4', + 'format_id': q, + }) - return [{ - 'id' : video_id, - 'url' : video_url, - 'ext' : ext, - 'title' : title, - 'thumbnail' : thumbnail_url, - 'upload_date' : upload_date, - 'view_count' : view_count, - }] + info = { + 'id': data_video['guid'], + 'title': compat_urllib_parse.unquote(data_video['title']), + 'formats': formats, + 'description': get_meta_content('description', webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + } + # TODO: Remove when #980 has been merged + info.update(formats[-1]) + return info diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 1405b73f7..79679a14a 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -7,15 +7,25 @@ from .common import InfoExtractor class TudouIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?' - _TEST = { + _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs|albumplay)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?' + _TESTS = [{ u'url': u'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', u'file': u'159448201.f4v', u'md5': u'140a49ed444bd22f93330985d8475fcb', u'info_dict': { u"title": u"卡马乔国足开大脚长传冲吊集锦" } - } + }, + { + u'url': u'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html', + u'file': u'todo.mp4', + u'md5': u'todo.mp4', + u'info_dict': { + u'title': u'todo.mp4', + }, + u'add_ie': [u'Youku'], + u'skip': u'Only works from China' + }] def _url_for_id(self, id, quality = None): info_url = "http://v2.tudou.com/f?id="+str(id) @@ -29,14 +39,18 @@ class TudouIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group(2) webpage = self._download_webpage(url, video_id) - title = re.search(",kw:\"(.+)\"",webpage) - if title is None: - title = re.search(",kw: \'(.+)\'",webpage) - title = title.group(1) - thumbnail_url = re.search(",pic: \'(.+?)\'",webpage) - if thumbnail_url is None: - thumbnail_url = re.search(",pic:\"(.+?)\"",webpage) - thumbnail_url = thumbnail_url.group(1) + + m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage) + if m and m.group(1): + return { + '_type': 'url', + 'url': u'youku:' + m.group(1), + 'ie_key': 'Youku' + } + + title = self._search_regex(r",kw:['\"](.+?)[\"']", webpage, u'title') + thumbnail_url = self._search_regex( + r",pic:\s*[\"'](.+?)[\"']", webpage, u'thumbnail URL', fatal=False) segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments') segments = json.loads(segs_json) diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py index 00fa2ccb5..9d88c17f5 100644 --- a/youtube_dl/extractor/youku.py +++ b/youtube_dl/extractor/youku.py @@ -13,7 +13,7 @@ from ..utils import ( class YoukuIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(v|player)\.youku\.com/(v_show/id_|player\.php/sid/)(?P<ID>[A-Za-z0-9]+)(\.html|/v.swf)' + _VALID_URL = r'(?:(?:http://)?(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|youku:)(?P<ID>[A-Za-z0-9]+)(?:\.html|/v\.swf|)' _TEST = { u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html", u"file": u"XNDgyMDQ2NTQw_part00.flv", |