1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-15 14:35:54 +01:00
yt-dlp/youtube_dl/extractor/howcast.py
Jaime Marquínez Ferrándiz 9f79463803 [howcast] update test's checksum
2013-11-22 21:25:12 +01:00

46 lines
1.7 KiB
Python

import re
from .common import InfoExtractor
class HowcastIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
_TEST = {
u'url': u'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
u'file': u'390161.mp4',
u'md5': u'8b743df908c42f60cf6496586c7f12c3',
u'info_dict': {
u"description": u"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot.",
u"title": u"How to Tie a Square Knot Properly"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_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,
}]