[jadorecettepub] Add extractor (Fixes #2148)

This commit is contained in:
Philipp Hagemeister 2014-02-08 19:20:11 +01:00
parent 98dbee8681
commit 9766538124
5 changed files with 60 additions and 9 deletions

View file

@ -85,7 +85,7 @@ def test_justin_tv_chapterid_matching(self):
self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
def test_youtube_extract(self):
assertExtractId = lambda url, id: self.assertEqual(YoutubeIE()._extract_id(url), id)
assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')

View file

@ -30,7 +30,7 @@ def test_youtube_playlist(self):
result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'ytdl test PL')
ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
def test_youtube_playlist_noplaylist(self):
@ -39,7 +39,7 @@ def test_youtube_playlist_noplaylist(self):
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertEqual(result['_type'], 'url')
self.assertEqual(YoutubeIE()._extract_id(result['url']), 'FXxLjLQi3Fg')
self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
def test_issue_673(self):
dl = FakeYDL()
@ -59,7 +59,7 @@ def test_youtube_playlist_with_deleted(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
self.assertFalse('pElCt5oNDuI' in ytie_results)
self.assertFalse('KdPEApIVdWM' in ytie_results)
@ -76,9 +76,9 @@ def test_youtube_course(self):
# TODO find a > 100 (paginating?) videos course
result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
entries = result['entries']
self.assertEqual(YoutubeIE()._extract_id(entries[0]['url']), 'j9WZyLZCBzs')
self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
self.assertEqual(len(entries), 25)
self.assertEqual(YoutubeIE()._extract_id(entries[-1]['url']), 'rYefUsYuEp0')
self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
def test_youtube_channel(self):
dl = FakeYDL()

View file

@ -105,6 +105,7 @@
IviIE,
IviCompilationIE
)
from .jadorecettepub import JadoreCettePubIE
from .jeuxvideo import JeuxVideoIE
from .jukebox import JukeboxIE
from .justintv import JustinTVIE

View file

@ -0,0 +1,49 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from .youtube import YoutubeIE
class JadoreCettePubIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?jadorecettepub\.com/[0-9]{4}/[0-9]{2}/(?P<id>.*?)\.html'
_TEST = {
'url': 'http://www.jadorecettepub.com/2010/12/star-wars-massacre-par-les-japonais.html',
'md5': '401286a06067c70b44076044b66515de',
'info_dict': {
'id': 'jLMja3tr7a4',
'ext': 'mp4',
'title': 'La pire utilisation de Star Wars',
'description': "Jadorecettepub.com vous a gratifié de plusieurs pubs géniales utilisant Star Wars et Dark Vador plus particulièrement... Mais l'heure est venue de vous proposer une version totalement massacrée, venue du Japon. Quand les Japonais détruisent l'image de Star Wars pour vendre du thon en boite, ça promet...",
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id')
webpage = self._download_webpage(url, display_id)
title = self._html_search_regex(
r'<span style="font-size: x-large;"><b>(.*?)</b></span>',
webpage, 'title')
description = self._html_search_regex(
r'(?s)<div id="fb-root">(.*?)<script>', webpage, 'description',
fatal=False)
real_url = self._search_regex(
r'\[/postlink\](.*)endofvid', webpage, 'video URL')
video_id = YoutubeIE.extract_id(real_url)
return {
'_type': 'url_transparent',
'url': real_url,
'id': video_id,
'title': title,
'description': description,
}

View file

@ -1085,8 +1085,9 @@ def _get_available_automatic_caption(self, video_id, webpage):
self._downloader.report_warning(err_msg)
return {}
def _extract_id(self, url):
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
@classmethod
def extract_id(cls, url):
mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(2)
@ -1115,7 +1116,7 @@ def _real_extract(self, url):
mobj = re.search(self._NEXT_URL_RE, url)
if mobj:
url = 'https://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
video_id = self._extract_id(url)
video_id = self.extract_id(url)
# Get video webpage
url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id