[trutube] Support multiple formats (#2433)

This commit is contained in:
Philipp Hagemeister 2014-02-22 15:05:30 +01:00
parent af284c6d1b
commit 491ed3dda2
2 changed files with 39 additions and 25 deletions

View File

@ -18,6 +18,7 @@ from test.helper import (
import hashlib
import io
import json
import re
import socket
import youtube_dl.YoutubeDL
@ -137,6 +138,15 @@ def generator(test_case):
with io.open(info_json_fn, encoding='utf-8') as infof:
info_dict = json.load(infof)
for (info_field, expected) in tc.get('info_dict', {}).items():
if isinstance(expected, compat_str) and expected.startswith('re:'):
got = info_dict.get(info_field)
match_str = expected[len('re:'):]
match_rex = re.compile(match_str)
self.assertTrue(
isinstance(got, compat_str) and match_rex.match(got),
u'field %s (value: %r) should match %r' % (info_field, got, match_str))
else:
if isinstance(expected, compat_str) and expected.startswith('md5:'):
got = 'md5:' + md5(info_dict.get(info_field))
else:

View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
@ -7,37 +9,39 @@ from ..utils import (
class TruTubeIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:www\.)?(?P<url>trutube\.tv/video/(?P<videoid>.*/.*))'
_VALID_URL = r'https?://(?:www\.)?trutube\.tv/video/(?P<id>[0-9]+)/.*'
_TEST = {
'url': ('http://www.trutube.tv/video/20814/Ernst-Zundel-met-les-Jui'
'fs-en-guarde-VOSTFR'),
'md5': '9973aa3c2870626799d2ac4e36cfc3dc',
'url': 'http://trutube.tv/video/14880/Ramses-II-Proven-To-Be-A-Red-Headed-Caucasoid-',
'md5': 'c5b6e301b0a2040b074746cbeaa26ca1',
'info_dict': {
u"title": u"TruTube.TV - Spitting in the face of die-versity",
u"ext": u"mp4"
'id': '14880',
'ext': 'flv',
'title': 'Ramses II - Proven To Be A Red Headed Caucasoid',
'thumbnail': 're:^http:.*\.jpg$',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = mobj.group('videoid')
# Get webpage content
webpage = self._download_webpage(url, video_id)
video_title = self._og_search_title(webpage).strip()
thumbnail = self._search_regex(
r"var splash_img = '([^']+)';", webpage, 'thumbnail', fatal=False)
# Get the video title
video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
webpage, 'title').strip()
video_url = self._search_regex(r'(http://.*\.(?:mp4|flv))',
webpage, u'video URL')
ext = video_url[-3:]
all_formats = re.finditer(
r"var (?P<key>[a-z]+)_video_file\s*=\s*'(?P<url>[^']+)';", webpage)
formats = [{
'format_id': m.group('key'),
'quality': -i,
'url': m.group('url'),
} for i, m in enumerate(all_formats)]
self._sort_formats(formats)
return {
'id': video_id,
'url': video_url,
'title': video_title,
'ext': ext
'formats': formats,
'thumbnail': thumbnail,
}