mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2025-07-24 06:11:36 -05:00
Compare commits
10 Commits
2014.04.21
...
2014.04.21
Author | SHA1 | Date | |
---|---|---|---|
3f0aae4244 | |||
48099643cc | |||
621f33c9d0 | |||
f07a9f6f43 | |||
e51880fd32 | |||
88ce273da4 | |||
b9ba5dfa28 | |||
4086f11929 | |||
478c2c6193 | |||
d2d6481afb |
@ -85,7 +85,7 @@ def gettestcases(include_onlymatching=False):
|
||||
else:
|
||||
tests = getattr(ie, '_TESTS', [])
|
||||
for t in tests:
|
||||
if not include_onlymatching and getattr(t, 'only_matching', False):
|
||||
if not include_onlymatching and t.get('only_matching', False):
|
||||
continue
|
||||
t['name'] = type(ie).__name__[:-len('IE')]
|
||||
yield t
|
||||
|
@ -40,6 +40,7 @@ from .cinemassacre import CinemassacreIE
|
||||
from .clipfish import ClipfishIE
|
||||
from .cliphunter import CliphunterIE
|
||||
from .clipsyndicate import ClipsyndicateIE
|
||||
from .clubic import ClubicIE
|
||||
from .cmt import CMTIE
|
||||
from .cnet import CNETIE
|
||||
from .cnn import (
|
||||
|
@ -74,7 +74,8 @@ class ArteTVPlus7IE(InfoExtractor):
|
||||
return self._extract_from_webpage(webpage, video_id, lang)
|
||||
|
||||
def _extract_from_webpage(self, webpage, video_id, lang):
|
||||
json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
|
||||
json_url = self._html_search_regex(
|
||||
r'arte_vp_url="(.*?)"', webpage, 'json vp url')
|
||||
return self._extract_from_json_url(json_url, video_id, lang)
|
||||
|
||||
def _extract_from_json_url(self, json_url, video_id, lang):
|
||||
|
58
youtube_dl/extractor/clubic.py
Normal file
58
youtube_dl/extractor/clubic.py
Normal file
@ -0,0 +1,58 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
qualities,
|
||||
)
|
||||
|
||||
|
||||
class ClubicIE(InfoExtractor):
|
||||
_VALID_URL = r'http://(?:www\.)?clubic\.com/video/[^/]+/video.*-(?P<id>[0-9]+)\.html'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html',
|
||||
'md5': '1592b694ba586036efac1776b0b43cd3',
|
||||
'info_dict': {
|
||||
'id': '448474',
|
||||
'ext': 'mp4',
|
||||
'title': 'Clubic Week 2.0 : le FBI se lance dans la photo d\u0092identité',
|
||||
'description': 're:Gueule de bois chez Nokia. Le constructeur a indiqué cette.*',
|
||||
'thumbnail': 're:^http://img\.clubic\.com/.*\.jpg$',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
player_url = 'http://player.m6web.fr/v1/player/clubic/%s.html' % video_id
|
||||
player_page = self._download_webpage(player_url, video_id)
|
||||
|
||||
config_json = self._search_regex(
|
||||
r'(?m)M6\.Player\.config\s*=\s*(\{.+?\});$', player_page,
|
||||
'configuration')
|
||||
config = json.loads(config_json)
|
||||
|
||||
video_info = config['videoInfo']
|
||||
sources = config['sources']
|
||||
quality_order = qualities(['sd', 'hq'])
|
||||
|
||||
formats = [{
|
||||
'format_id': src['streamQuality'],
|
||||
'url': src['src'],
|
||||
'quality': quality_order(src['streamQuality']),
|
||||
} for src in sources]
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': video_info['title'],
|
||||
'formats': formats,
|
||||
'description': clean_html(video_info.get('description')),
|
||||
'thumbnail': config.get('poster'),
|
||||
}
|
@ -33,7 +33,7 @@ class CNETIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
data_json = self._html_search_regex(
|
||||
r"<div class=\"cnetVideoPlayer\" data-cnet-video-options='([^']+)'",
|
||||
r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
|
||||
webpage, 'data json')
|
||||
data = json.loads(data_json)
|
||||
vdata = data['video']
|
||||
|
@ -531,7 +531,7 @@ class GenericIE(InfoExtractor):
|
||||
return OoyalaIE._build_url_result(mobj.group('ec'))
|
||||
|
||||
# Look for Aparat videos
|
||||
mobj = re.search(r'<iframe src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
|
||||
mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
|
||||
if mobj is not None:
|
||||
return self.url_result(mobj.group(1), 'Aparat')
|
||||
|
||||
|
@ -3,9 +3,6 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
class MDRIE(InfoExtractor):
|
||||
|
@ -97,7 +97,7 @@ class TEDIE(SubtitlesInfoExtractor):
|
||||
playlist_info = info['playlist']
|
||||
|
||||
playlist_entries = [
|
||||
self.url_result(u'http://www.ted.com/talks/' + talk['slug'], self.ie_key())
|
||||
self.url_result('http://www.ted.com/talks/' + talk['slug'], self.ie_key())
|
||||
for talk in info['talks']
|
||||
]
|
||||
return self.playlist_result(
|
||||
@ -163,7 +163,7 @@ class TEDIE(SubtitlesInfoExtractor):
|
||||
sub_lang_list[l] = url
|
||||
return sub_lang_list
|
||||
else:
|
||||
self._downloader.report_warning(u'video doesn\'t have subtitles')
|
||||
self._downloader.report_warning('video doesn\'t have subtitles')
|
||||
return {}
|
||||
|
||||
def _watch_info(self, url, name):
|
||||
@ -178,7 +178,10 @@ class TEDIE(SubtitlesInfoExtractor):
|
||||
title = self._html_search_regex(
|
||||
r"(?s)<h1(?:\s+class='[^']+')?>(.+?)</h1>", webpage, 'title')
|
||||
description = self._html_search_regex(
|
||||
r'(?s)<h4 class="[^"]+" id="h3--about-this-talk">.*?</h4>(.*?)</div>',
|
||||
[
|
||||
r'(?s)<h4 class="[^"]+" id="h3--about-this-talk">.*?</h4>(.*?)</div>',
|
||||
r'(?s)<p><strong>About this talk:</strong>\s+(.*?)</p>',
|
||||
],
|
||||
webpage, 'description', fatal=False)
|
||||
|
||||
return {
|
||||
|
@ -1406,3 +1406,14 @@ US_RATINGS = {
|
||||
|
||||
def strip_jsonp(code):
|
||||
return re.sub(r'(?s)^[a-zA-Z_]+\s*\(\s*(.*)\);\s*?\s*$', r'\1', code)
|
||||
|
||||
|
||||
def qualities(quality_ids):
|
||||
""" Get a numeric quality value out of a list of possible values """
|
||||
def q(qid):
|
||||
try:
|
||||
return quality_ids.index(qid)
|
||||
except ValueError:
|
||||
return -1
|
||||
return q
|
||||
|
||||
|
@ -1,2 +1,2 @@
|
||||
|
||||
__version__ = '2014.04.21.1'
|
||||
__version__ = '2014.04.21.3'
|
||||
|
Reference in New Issue
Block a user