2014-01-23 03:05:58 +00:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2016-04-09 13:47:12 +00:00
|
|
|
from .common import InfoExtractor
|
2016-09-04 08:25:59 +00:00
|
|
|
from ..utils import js_to_json
|
2013-10-12 20:21:23 +00:00
|
|
|
|
|
|
|
|
2016-04-09 13:47:12 +00:00
|
|
|
class RottenTomatoesIE(InfoExtractor):
|
2013-10-12 20:21:23 +00:00
|
|
|
_VALID_URL = r'https?://www\.rottentomatoes\.com/m/[^/]+/trailers/(?P<id>\d+)'
|
|
|
|
|
|
|
|
_TEST = {
|
2014-01-23 03:05:58 +00:00
|
|
|
'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/',
|
|
|
|
'info_dict': {
|
2016-09-04 08:25:59 +00:00
|
|
|
'id': '11028566',
|
2015-02-01 11:11:14 +00:00
|
|
|
'ext': 'mp4',
|
2016-04-09 13:47:12 +00:00
|
|
|
'title': 'Toy Story 3',
|
2016-09-04 08:25:59 +00:00
|
|
|
'thumbnail': 're:^https?://.*\.jpg$',
|
2013-10-12 20:21:23 +00:00
|
|
|
},
|
|
|
|
}
|
2016-04-09 13:47:12 +00:00
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
video_id = self._match_id(url)
|
|
|
|
webpage = self._download_webpage(url, video_id)
|
2016-09-04 08:25:59 +00:00
|
|
|
|
|
|
|
params = self._parse_json(
|
|
|
|
self._search_regex(r'(?s)RTVideo\(({.+?})\);', webpage, 'player parameters'),
|
|
|
|
video_id, transform_source=lambda s: js_to_json(s.replace('window.location.href', '""')))
|
|
|
|
|
|
|
|
formats = []
|
|
|
|
if params.get('urlHLS'):
|
|
|
|
formats.extend(self._extract_m3u8_formats(
|
|
|
|
params['urlHLS'], video_id, ext='mp4',
|
|
|
|
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
|
|
|
|
if params.get('urlMP4'):
|
|
|
|
formats.append({
|
|
|
|
'url': params['urlMP4'],
|
|
|
|
'format_id': 'mp4',
|
|
|
|
})
|
|
|
|
self._sort_formats(formats)
|
2016-04-09 13:47:12 +00:00
|
|
|
|
|
|
|
return {
|
2016-09-04 08:25:59 +00:00
|
|
|
'id': video_id,
|
2016-04-09 13:47:12 +00:00
|
|
|
'title': self._og_search_title(webpage),
|
2016-09-04 08:25:59 +00:00
|
|
|
'formats': formats,
|
|
|
|
'thumbnail': params.get('thumbnailImg'),
|
2016-04-09 13:47:12 +00:00
|
|
|
}
|