From 59f4fd4dc65f0576fdf02bfb710cddc90262b1ba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sun, 12 May 2013 14:05:14 +0200 Subject: [PATCH] YahooIE: remove old code and accept screen.yahoo.com videos (#300) Videos require rtmpdump --- test/tests.json | 10 +++ youtube_dl/InfoExtractors.py | 146 +++++++++-------------------------- 2 files changed, 47 insertions(+), 109 deletions(-) diff --git a/test/tests.json b/test/tests.json index 5a14b0523..f0e5cd8bf 100644 --- a/test/tests.json +++ b/test/tests.json @@ -430,5 +430,15 @@ "info_dict":{ "title":"François Hollande \"Je crois que c'est clair\"" } + }, + { + "name": "Yahoo", + "url": "http://screen.yahoo.com/obama-celebrates-iraq-victory-27592561.html", + "file": "27592561.flv", + "md5": "c6179bed843512823fd284fa2e7f012d", + "info_dict": { + "title": "Obama Celebrates Iraq Victory" + }, + "skip": "Requires rtmpdump" } ] diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index ec52cbcff..789f9872e 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -912,123 +912,51 @@ class PhotobucketIE(InfoExtractor): class YahooIE(InfoExtractor): - """Information extractor for video.yahoo.com.""" + """Information extractor for screen.yahoo.com.""" + _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P\d*?)\.html' - _WORKING = False - # _VALID_URL matches all Yahoo! Video URLs - # _VPAGE_URL matches only the extractable '/watch/' URLs - _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' - _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' - IE_NAME = u'video.yahoo' - - def _real_extract(self, url, new_video=True): - # Extract ID from URL + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: raise ExtractorError(u'Invalid URL: %s' % url) + video_id = mobj.group('id') - video_id = mobj.group(2) - video_extension = 'flv' - - # Rewrite valid but non-extractable URLs as - # extractable English language /watch/ URLs - if re.match(self._VPAGE_URL, url) is None: - request = compat_urllib_request.Request(url) - try: - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err)) - - mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract id field') - yahoo_id = mobj.group(1) - - mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract vid field') - yahoo_vid = mobj.group(1) - - url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) - return self._real_extract(url, new_video=False) - - # Retrieve video webpage to extract further information - request = compat_urllib_request.Request(url) - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err)) - - # Extract uploader and title from webpage + # TODO: Check which url parameters are required + info_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;lmsoverride=1;outputformat=mrss;cb=974419660;id=%s;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id + webpage = self._download_webpage(info_url, video_id, "Downloading info webpage") + info_re = r'''<!\[CDATA\[(?P<title>.*?)\]\]>.* + .*?)\]\]>.* + .*?)\ .*\]\]>.* + ', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract video title') - video_title = mobj.group(1).decode('utf-8') + m_info = re.search(info_re, webpage, re.VERBOSE|re.DOTALL) + if m_info is None: + raise ExtractorError(u'Unable to extract video info') + video_title = m_info.group('title') + video_description = m_info.group('description') + video_thumb = m_info.group('thumb') + video_date = m_info.group('date') + video_date = datetime.datetime.strptime(video_date, '%m/%d/%Y').strftime('%Y%m%d') - mobj = re.search(r'

(.*)

', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract video uploader') - video_uploader = mobj.group(1).decode('utf-8') - - # Extract video thumbnail - mobj = re.search(r'', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract video thumbnail') - video_thumbnail = mobj.group(1).decode('utf-8') - - # Extract video description - mobj = re.search(r'', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract video description') - video_description = mobj.group(1).decode('utf-8') - if not video_description: - video_description = 'No description available.' - - # Extract video height and width - mobj = re.search(r'', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract video height') - yv_video_height = mobj.group(1) - - mobj = re.search(r'', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract video width') - yv_video_width = mobj.group(1) - - # Retrieve video playlist to extract media URL - # I'm not completely sure what all these options are, but we - # seem to need most of them, otherwise the server sends a 401. - yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents - yv_bitrate = '700' # according to Wikipedia this is hard-coded - request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + - '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + - '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err)) - - # Extract media URL from playlist XML - mobj = re.search(r'