diff options
author | Filippo Valsorda <filippo.valsorda@gmail.com> | 2013-06-09 14:21:42 +0200 |
---|---|---|
committer | Filippo Valsorda <filippo.valsorda@gmail.com> | 2013-06-09 14:21:42 +0200 |
commit | 78d3442b1209d3858cfea1f7ca958f661784b5ab (patch) | |
tree | 7b9a5ff20a2f9a6448a6795698b2117b336a8549 /youtube_dl/InfoExtractors.py | |
parent | 979a9dd4c4d46e0f2b11bc4bcac51ad8d446d186 (diff) |
test: extend the reach of info_dict checking
* print the info_dict in a format suitable to easy adding to tests.json during tests if un-tested fields are detected
* make it possible to put the crc32 in tests.json if the field is too long
* complete the "info_dict" fields in existing tests
* fixed the bugs catched doing this
Diffstat (limited to 'youtube_dl/InfoExtractors.py')
-rwxr-xr-x | youtube_dl/InfoExtractors.py | 17 |
1 files changed, 10 insertions, 7 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 6060a5988..24e9c4cc7 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -2377,8 +2377,8 @@ class EscapistIE(InfoExtractor): showName = mobj.group('showname') videoId = mobj.group('episode') - self.report_extraction(showName) - webpage = self._download_webpage(url, showName) + self.report_extraction(videoId) + webpage = self._download_webpage(url, videoId) videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"', webpage, u'description', fatal=False) @@ -2389,10 +2389,13 @@ class EscapistIE(InfoExtractor): playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"', webpage, u'player url') + title = self._html_search_regex('<meta name="title" content="([^"]*)"', + webpage, u'player url').split(' : ')[-1] + configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url') configUrl = compat_urllib_parse.unquote(configUrl) - configJSON = self._download_webpage(configUrl, showName, + configJSON = self._download_webpage(configUrl, videoId, u'Downloading configuration', u'unable to download configuration') @@ -2412,7 +2415,7 @@ class EscapistIE(InfoExtractor): 'url': videoUrl, 'uploader': showName, 'upload_date': None, - 'title': showName, + 'title': title, 'ext': 'mp4', 'thumbnail': imgUrl, 'description': videoDesc, @@ -3581,14 +3584,14 @@ class YouPornIE(InfoExtractor): size = format[0] bitrate = format[1] format = "-".join( format ) - title = u'%s-%s-%s' % (video_title, size, bitrate) + # title = u'%s-%s-%s' % (video_title, size, bitrate) formats.append({ 'id': video_id, 'url': video_url, 'uploader': video_uploader, 'upload_date': upload_date, - 'title': title, + 'title': video_title, 'ext': extension, 'format': format, 'thumbnail': thumbnail, @@ -4328,7 +4331,7 @@ class XHamsterIE(InfoExtractor): video_upload_date = None self._downloader.report_warning(u'Unable to extract upload date') - video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^>]+)', + video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)', webpage, u'uploader id', default=u'anonymous') video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'', |