1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 00:17:43 +00:00
youtube-dl/youtube_dl/extractor/howstuffworks.py

91 lines
3.4 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
find_xpath_attr,
int_or_none,
js_to_json,
unescapeHTML,
2016-03-31 20:09:27 +00:00
determine_ext,
)
class HowStuffWorksIE(InfoExtractor):
_VALID_URL = r'https?://[\da-z-]+\.(?:howstuffworks|stuff(?:(?:youshould|theydontwantyouto)know|toblowyourmind|momnevertoldyou)|(?:brain|car)stuffshow|fwthinking|geniusstuff)\.com/(?:[^/]+/)*(?:\d+-)?(?P<id>.+?)-video\.htm'
_TESTS = [
{
'url': 'http://www.stufftoblowyourmind.com/videos/optical-illusions-video.htm',
'md5': '76646a5acc0c92bf7cd66751ca5db94d',
'info_dict': {
'id': '855410',
2016-03-31 20:09:27 +00:00
'ext': 'mp4',
'title': 'Your Trickster Brain: Optical Illusions -- Science on the Web',
'description': 'md5:e374ff9561f6833ad076a8cc0a5ab2fb',
},
},
2015-07-17 15:43:27 +00:00
{
'url': 'http://shows.howstuffworks.com/more-shows/why-does-balloon-stick-to-hair-video.htm',
2015-07-17 16:07:55 +00:00
'only_matching': True,
2015-07-17 15:43:27 +00:00
}
]
def _real_extract(self, url):
2014-12-04 23:09:17 +00:00
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
clip_js = self._search_regex(
r'(?s)var clip = ({.*?});', webpage, 'clip info')
clip_info = self._parse_json(
clip_js, display_id, transform_source=js_to_json)
2014-12-05 18:46:49 +00:00
video_id = clip_info['content_id']
formats = []
m3u8_url = clip_info.get('m3u8')
2016-03-31 20:09:27 +00:00
if m3u8_url and determine_ext(m3u8_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', format_id='hls', fatal=True))
flv_url = clip_info.get('flv_url')
if flv_url:
formats.append({
'url': flv_url,
'format_id': 'flv',
})
for video in clip_info.get('mp4', []):
2014-12-04 23:09:17 +00:00
formats.append({
'url': video['src'],
2016-03-31 20:09:27 +00:00
'format_id': 'mp4-%s' % video['bitrate'],
'vbr': int_or_none(video['bitrate'].rstrip('k')),
2014-12-04 23:09:17 +00:00
})
2014-12-05 18:46:49 +00:00
if not formats:
smil = self._download_xml(
'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % video_id,
video_id, 'Downloading video SMIL')
http_base = find_xpath_attr(
smil,
'./{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'),
'name',
'httpBase').get('content')
URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=A&g=A'
for video in smil.findall(
'./{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')):
vbr = int_or_none(video.attrib['system-bitrate'], scale=1000)
2014-12-05 18:46:49 +00:00
formats.append({
'url': '%s/%s%s' % (http_base, video.attrib['src'], URL_SUFFIX),
'format_id': '%dk' % vbr,
'vbr': vbr,
})
self._sort_formats(formats)
return {
'id': '%s' % video_id,
'display_id': display_id,
'title': unescapeHTML(clip_info['clip_title']),
'description': unescapeHTML(clip_info.get('caption')),
'thumbnail': clip_info.get('video_still_url'),
2016-03-31 20:09:27 +00:00
'duration': int_or_none(clip_info.get('duration')),
'formats': formats,
}