[trutube] Fix extraction

This commit is contained in:
Sergey M․ 2014-10-29 21:16:10 +07:00
parent 8abec2c8bb
commit c451d4f553

View file

@ -1,13 +1,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import xpath_text
class TruTubeIE(InfoExtractor): class TruTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?trutube\.tv/video/(?P<id>[0-9]+)/.*' _VALID_URL = r'https?://(?:www\.)?trutube\.tv/(?:video/|nuevo/player/embed\.php\?v=)(?P<id>[0-9]+)'
_TEST = { _TESTS = [{
'url': 'http://trutube.tv/video/14880/Ramses-II-Proven-To-Be-A-Red-Headed-Caucasoid-', 'url': 'http://trutube.tv/video/14880/Ramses-II-Proven-To-Be-A-Red-Headed-Caucasoid-',
'md5': 'c5b6e301b0a2040b074746cbeaa26ca1', 'md5': 'c5b6e301b0a2040b074746cbeaa26ca1',
'info_dict': { 'info_dict': {
@ -16,29 +15,26 @@ class TruTubeIE(InfoExtractor):
'title': 'Ramses II - Proven To Be A Red Headed Caucasoid', 'title': 'Ramses II - Proven To Be A Red Headed Caucasoid',
'thumbnail': 're:^http:.*\.jpg$', 'thumbnail': 're:^http:.*\.jpg$',
} }
} }, {
'url': 'https://trutube.tv/nuevo/player/embed.php?v=14880',
'only_matching': True,
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) config = self._download_xml(
video_title = self._og_search_title(webpage).strip() 'https://trutube.tv/nuevo/player/config.php?v=%s' % video_id,
thumbnail = self._search_regex( video_id, transform_source=lambda s: s.strip())
r"var splash_img = '([^']+)';", webpage, 'thumbnail', fatal=False)
all_formats = re.finditer( # filehd is always 404
r"var (?P<key>[a-z]+)_video_file\s*=\s*'(?P<url>[^']+)';", webpage) video_url = xpath_text(config, './file', 'video URL', fatal=True)
formats = [{ title = xpath_text(config, './title', 'title')
'format_id': m.group('key'), thumbnail = xpath_text(config, './image', ' thumbnail')
'quality': -i,
'url': m.group('url'),
} for i, m in enumerate(all_formats)]
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': video_title, 'url': video_url,
'formats': formats, 'title': title,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
} }