1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00

Add support for tou.tv (Fixes #1792)

This commit is contained in:
Philipp Hagemeister 2013-11-20 06:13:19 +01:00
parent 69545c2aff
commit 5904088811
4 changed files with 106 additions and 0 deletions

View file

@ -133,6 +133,7 @@ from .techtalks import TechTalksIE
from .ted import TEDIE
from .tf1 import TF1IE
from .thisav import ThisAVIE
from .toutv import TouTvIE
from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE
from .tube8 import Tube8IE

View file

@ -350,6 +350,17 @@ class InfoExtractor(object):
if secure: regexes = self._og_regexes('video:secure_url') + regexes
return self._html_search_regex(regexes, html, name, **kargs)
def _html_search_meta(self, name, html, display_name=None):
if display_name is None:
display_name = name
return self._html_search_regex(
r'''(?ix)<meta(?=[^>]+(?:name|property)=["\']%s["\'])
[^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
html, display_name, fatal=False)
def _dc_search_uploader(self, html):
return self._html_search_meta('dc.creator', html, 'uploader')
def _rta_search(self, html):
# See http://www.rtalabel.org/index.php?content=howtofaq#single
if re.search(r'(?ix)<meta\s+name="rating"\s+'
@ -358,6 +369,23 @@ class InfoExtractor(object):
return 18
return 0
def _media_rating_search(self, html):
# See http://www.tjg-designs.com/WP/metadata-code-examples-adding-metadata-to-your-web-pages/
rating = self._html_search_meta('rating', html)
if not rating:
return None
RATING_TABLE = {
'safe for kids': 0,
'general': 8,
'14 years': 14,
'mature': 17,
'restricted': 19,
}
return RATING_TABLE.get(rating.lower(), None)
class SearchInfoExtractor(InfoExtractor):
"""

View file

@ -0,0 +1,75 @@
# coding: utf-8
import re
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
ExtractorError,
unified_strdate,
)
class TouTvIE(InfoExtractor):
IE_NAME = u'tou.tv'
_VALID_URL = r'https?://www\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/(?P<episode>S[0-9]+E[0-9]+)))'
_TEST = {
u'url': u'http://www.tou.tv/30-vies/S04E41',
u'file': u'30-vies_S04E41.mp4',
u'info_dict': {
u'title': u'30 vies Saison 4 / Épisode 41',
u'description': u'md5:da363002db82ccbe4dafeb9cab039b09',
u'age_limit': 8,
u'uploader': u'Groupe des Nouveaux Médias',
u'duration': 1296,
u'upload_date': u'20131118',
u'thumbnail': u'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg',
},
u'params': {
u'skip_download': True, # Requires rtmpdump
},
u'xskip': 'Only available in Canada'
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
mediaId = self._search_regex(
r'"idMedia":\s*"([^"]+)"', webpage, u'media ID')
# TODO test from de
streams_url = u'http://release.theplatform.com/content.select?pid=' + mediaId
streams_webpage = self._download_webpage(
streams_url, video_id, note=u'Downloading stream list')
streams_doc = xml.etree.ElementTree.fromstring(
streams_webpage.encode('utf-8'))
video_url = next(n.text
for n in streams_doc.findall('.//choice/url')
if u'//ad.doubleclick' not in n.text)
if video_url.endswith('/Unavailable.flv'):
raise ExtractorError(
u'Access to this video is blocked from outside of Canada',
expected=True)
duration_str = self._html_search_meta(
'video:duration', webpage, u'duration')
duration = int(duration_str) if duration_str else None
upload_date_str = self._html_search_meta(
'video:release_date', webpage, u'upload date')
upload_date = unified_strdate(upload_date_str) if upload_date_str else None
return {
'id': video_id,
'title': self._og_search_title(webpage),
'url': video_url,
'description': self._og_search_description(webpage),
'uploader': self._dc_search_uploader(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'age_limit': self._media_rating_search(webpage),
'duration': duration,
'upload_date': upload_date,
'ext': 'mp4',
}

View file

@ -734,6 +734,8 @@ def unified_strdate(date_str):
'%Y/%m/%d %H:%M:%S',
'%d.%m.%Y %H:%M',
'%Y-%m-%dT%H:%M:%SZ',
'%Y-%m-%dT%H:%M:%S.%fZ',
'%Y-%m-%dT%H:%M:%S.%f0Z',
'%Y-%m-%dT%H:%M:%S',
]
for expression in format_expressions: