1 from __future__ import unicode_literals
3 from .common import InfoExtractor
13 class HowStuffWorksIE(InfoExtractor):
14 _VALID_URL = r'https?://[\da-z-]+\.howstuffworks\.com/(?:[^/]+/)*(?:\d+-)?(?P<id>.+?)-video\.htm'
17 'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm',
21 'title': 'Cool Jobs - Iditarod Musher',
22 'description': 'Cold sleds, freezing temps and warm dog breath... an Iditarod musher\'s dream. Kasey-Dee Gardner jumps on a sled to find out what the big deal is.',
23 'display_id': 'cool-jobs-iditarod-musher',
24 'thumbnail': 're:^https?://.*\.jpg$',
29 'url': 'http://adventure.howstuffworks.com/7199-survival-zone-food-and-water-in-the-savanna-video.htm',
33 'title': 'Survival Zone: Food and Water In the Savanna',
34 'description': 'Learn how to find both food and water while trekking in the African savannah. In this video from the Discovery Channel.',
35 'display_id': 'survival-zone-food-and-water-in-the-savanna',
36 'thumbnail': 're:^https?://.*\.jpg$',
40 'url': 'http://entertainment.howstuffworks.com/arts/2706-sword-swallowing-1-by-dan-meyer-video.htm',
44 'title': 'Sword Swallowing #1 by Dan Meyer',
45 'description': 'Video footage (1 of 3) used by permission of the owner Dan Meyer through Sword Swallowers Association International <www.swordswallow.org>',
46 'display_id': 'sword-swallowing-1-by-dan-meyer',
47 'thumbnail': 're:^https?://.*\.jpg$',
51 'url': 'http://shows.howstuffworks.com/stuff-to-blow-your-mind/optical-illusions-video.htm',
52 'only_matching': True,
56 def _real_extract(self, url):
57 display_id = self._match_id(url)
58 webpage = self._download_webpage(url, display_id)
59 clip_js = self._search_regex(
60 r'(?s)var clip = ({.*?});', webpage, 'clip info')
61 clip_info = self._parse_json(
62 clip_js, display_id, transform_source=js_to_json)
64 video_id = clip_info['content_id']
66 m3u8_url = clip_info.get('m3u8')
67 if m3u8_url and determine_ext(m3u8_url) == 'm3u8':
68 formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', format_id='hls', fatal=True))
69 flv_url = clip_info.get('flv_url')
75 for video in clip_info.get('mp4', []):
78 'format_id': 'mp4-%s' % video['bitrate'],
79 'vbr': int_or_none(video['bitrate'].rstrip('k')),
83 smil = self._download_xml(
84 'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % video_id,
85 video_id, 'Downloading video SMIL')
87 http_base = find_xpath_attr(
89 './{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'),
91 'httpBase').get('content')
93 URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=A&g=A'
95 for video in smil.findall(
96 './{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')):
97 vbr = int_or_none(video.attrib['system-bitrate'], scale=1000)
99 'url': '%s/%s%s' % (http_base, video.attrib['src'], URL_SUFFIX),
100 'format_id': '%dk' % vbr,
104 self._sort_formats(formats)
107 'id': '%s' % video_id,
108 'display_id': display_id,
109 'title': unescapeHTML(clip_info['clip_title']),
110 'description': unescapeHTML(clip_info.get('caption')),
111 'thumbnail': clip_info.get('video_still_url'),
112 'duration': int_or_none(clip_info.get('duration')),