diff options
-rwxr-xr-x | youtube_dl/InfoExtractors.py | 34 | ||||
-rw-r--r-- | youtube_dl/extractor/howcast.py | 37 |
2 files changed, 38 insertions, 33 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 4bb4aa8..cc685e2 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -34,6 +34,7 @@ from .extractor.gametrailers import GametrailersIE from .extractor.generic import GenericIE from .extractor.googleplus import GooglePlusIE from .extractor.googlesearch import GoogleSearchIE +from .extractor.howcast import HowcastIE from .extractor.hypem import HypemIE from .extractor.ina import InaIE from .extractor.infoq import InfoQIE @@ -106,39 +107,6 @@ from .extractor.zdf import ZDFIE -class HowcastIE(InfoExtractor): - """Information Extractor for Howcast.com""" - _VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - webpage_url = 'http://www.howcast.com/videos/' + video_id - webpage = self._download_webpage(webpage_url, video_id) - - self.report_extraction(video_id) - - video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)', - webpage, u'video URL') - - video_title = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'', - webpage, u'title') - - video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'', - webpage, u'description', fatal=False) - - thumbnail = self._html_search_regex(r'<meta content=\'(.+?)\' property=\'og:image\'', - webpage, u'thumbnail', fatal=False) - - return [{ - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': video_title, - 'description': video_description, - 'thumbnail': thumbnail, - }] class FlickrIE(InfoExtractor): diff --git a/youtube_dl/extractor/howcast.py b/youtube_dl/extractor/howcast.py new file mode 100644 index 0000000..7b94f85 --- /dev/null +++ b/youtube_dl/extractor/howcast.py @@ -0,0 +1,37 @@ +import re + +from .common import InfoExtractor + + +class HowcastIE(InfoExtractor): + _VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + + video_id = mobj.group('id') + webpage_url = 'http://www.howcast.com/videos/' + video_id + webpage = self._download_webpage(webpage_url, video_id) + + self.report_extraction(video_id) + + video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)', + webpage, u'video URL') + + video_title = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'', + webpage, u'title') + + video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'', + webpage, u'description', fatal=False) + + thumbnail = self._html_search_regex(r'<meta content=\'(.+?)\' property=\'og:image\'', + webpage, u'thumbnail', fatal=False) + + return [{ + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': video_title, + 'description': video_description, + 'thumbnail': thumbnail, + }] |