[madmoizelle] add multiple videos support.
This commit is contained in:
Jonathan Nifenecker
parent
04ff0c5771
commit
c883416c48
@ -2,31 +2,49 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
from ..utils import (
|
||||
HEADRequest,
|
||||
)
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class MadmoizelleIE(InfoExtractor):
|
||||
IE_NAME = 'madmoizelle.com'
|
||||
IE_DESC = 'madmoizelle JW player'
|
||||
_VALID_URL = r'(https?://)?(?:www\.)?madmoizelle\.com/.+-(?P<id>[0-9]+)#?.*'
|
||||
IE_DESC = 'madmoizelle.com video:article'
|
||||
_VALID_URL = r'https?://(?:www\.)?madmoizelle\.com/.+-(?P<id>[0-9]+)#?.*'
|
||||
_TESTS = [{
|
||||
# classic video from the site
|
||||
# site's video in banner
|
||||
'url': 'http://www.madmoizelle.com/american-ultra-marion-seclin-408959#gs.nNBitsc',
|
||||
'info_dict': {
|
||||
'ext': 'mp4',
|
||||
'id': '408959',
|
||||
'title': 'Ma vie, c\'est comme dans American Ultra (Marion Seclin)',
|
||||
'description': 'md5:af3f8fc3b0668ede24feb1d50826e00c',
|
||||
}
|
||||
}, {
|
||||
# external video in banner
|
||||
'url': 'http://www.madmoizelle.com/game-of-thrones-saison-5-podcast-383647#gs.MvCyYtg',
|
||||
'info_dict': {
|
||||
'ext': 'mp4',
|
||||
'description': 'md5:efe603274fe803d27f9cb912eb83491a',
|
||||
'title': 'REPLAY ! L\'éMymyssion - Bilan Game of Thrones saison 5',
|
||||
'id': 'hH__bkW5Hu0',
|
||||
'upload_date': '20150623',
|
||||
'uploader_id': 'madmoiZelledotcom',
|
||||
'uploader': 'madmoiZelle.com',
|
||||
},
|
||||
}, {
|
||||
# site's video in banner and external video in content
|
||||
'url': 'http://www.madmoizelle.com/ukulete-episode-1-408599',
|
||||
'md5': 'e79ce7c2131cb3dfd200bea5177236fe',
|
||||
'info_dict': {
|
||||
'ext': 'mp4',
|
||||
'id': '408599',
|
||||
'title': 'Ukul’été - Épisode 1 - Plus besoin de radio !',
|
||||
'description': 'La voilà, la nouvelle saga de l’été, présentée par Marion et Waxx, plus excitante que Camping Paradis, plus addictive que Maigret, plus palpitante que Zodiac !',
|
||||
'description': 'md5:18949f6512cbd285c7b8b536a9955f06',
|
||||
}
|
||||
}, {
|
||||
# to test youtube redirection fallback
|
||||
# external video in content
|
||||
'url': 'http://www.madmoizelle.com/connected-court-metrage-501199#gs.AblS7VA',
|
||||
'md5': '77928d3964eceb2fe828204db5ee714a',
|
||||
'md5': '320890bbce5968e3482059a5d3770ba9',
|
||||
'info_dict': {
|
||||
'title': '\'Connected\' - A Sci-Fi Short Starring Pamela Anderson',
|
||||
'id': 'iWLcWHYmgpg',
|
||||
@ -35,45 +53,47 @@ class MadmoizelleIE(InfoExtractor):
|
||||
'description': 'md5:8de82e60853651512fb923e84873f526',
|
||||
'uploader': 'Motherboard',
|
||||
'uploader_id': 'MotherboardTV',
|
||||
'age_limit': 18,
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
|
||||
description = self._html_search_meta('description', webpage)
|
||||
|
||||
formats = []
|
||||
for format in re.finditer('jwplayer.*"(?P<url>[0-9]+.*(?P<quality>hd|sd).+)"', webpage):
|
||||
url = 'https://player.vimeo.com/external/' + format.group('url')
|
||||
# all article page may contain one video in a banner form,
|
||||
# and many externals videos in the article content
|
||||
results = []
|
||||
|
||||
# the url found point to a header redirection that we must follow
|
||||
head_req = HEADRequest(url)
|
||||
head_response = self._request_webpage(
|
||||
head_req, video_id,
|
||||
note=False, errnote='Could not send HEAD request to %s' % url,
|
||||
fatal=False)
|
||||
if head_response is not False:
|
||||
new_url = (self.url_result(head_response.geturl()))['url']
|
||||
if '<div class="video_single">' in webpage:
|
||||
# banner video present
|
||||
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
|
||||
description = self._html_search_meta('description', webpage)
|
||||
formats = []
|
||||
for format in re.finditer('jwplayer.*"(?P<url>[0-9]+.*(?P<quality>hd|sd).+)"', webpage):
|
||||
formats.append({
|
||||
'format_id': format.group('quality'),
|
||||
'url': 'https://player.vimeo.com/external/' + format.group('url'),
|
||||
})
|
||||
|
||||
formats.append({
|
||||
'format_id': format.group('quality'),
|
||||
'url': new_url,
|
||||
if formats:
|
||||
# site's jw player url found
|
||||
results.append({
|
||||
'formats': formats,
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
})
|
||||
|
||||
# external video, may be any site, in any number
|
||||
# fallback to generic extractor
|
||||
for external_vid in re.finditer(r'<iframe.*src="(?P<url>.*?)".*</iframe>', webpage):
|
||||
results.append({
|
||||
'url': external_vid.group('url'),
|
||||
'_type': 'url',
|
||||
})
|
||||
|
||||
if not formats:
|
||||
# nothing has been found with the site's extractor,
|
||||
# fallback to generic with original url
|
||||
return {
|
||||
'url': url,
|
||||
'ie_key': 'Generic',
|
||||
'_type': 'url',
|
||||
}
|
||||
else:
|
||||
return {
|
||||
'formats': formats,
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
}
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'entries': results,
|
||||
}
|
||||
|
||||
@ -1,137 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import hashlib
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
class WatIE(InfoExtractor):
|
||||
_VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html'
|
||||
IE_NAME = 'wat.tv'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
|
||||
'md5': 'ce70e9223945ed26a8056d413ca55dc9',
|
||||
'info_dict': {
|
||||
'id': '11713067',
|
||||
'display_id': 'soupe-figues-l-orange-aux-epices',
|
||||
'ext': 'mp4',
|
||||
'title': 'Soupe de figues à l\'orange et aux épices',
|
||||
'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
|
||||
'upload_date': '20140819',
|
||||
'duration': 120,
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
|
||||
'md5': 'fbc84e4378165278e743956d9c1bf16b',
|
||||
'info_dict': {
|
||||
'id': '11713075',
|
||||
'display_id': 'gregory-lemarchal-voix-ange',
|
||||
'ext': 'mp4',
|
||||
'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)',
|
||||
'description': 'md5:b7a849cf16a2b733d9cd10c52906dee3',
|
||||
'upload_date': '20140816',
|
||||
'duration': 2910,
|
||||
},
|
||||
'skip': "Ce contenu n'est pas disponible pour l'instant.",
|
||||
},
|
||||
]
|
||||
|
||||
def download_video_info(self, real_id):
|
||||
# 'contentv4' is used in the website, but it also returns the related
|
||||
# videos, we don't need them
|
||||
info = self._download_json('http://www.wat.tv/interface/contentv3/' + real_id, real_id)
|
||||
return info['media']
|
||||
|
||||
def _real_extract(self, url):
|
||||
def real_id_for_chapter(chapter):
|
||||
return chapter['tc_start'].split('-')[0]
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
short_id = mobj.group('short_id')
|
||||
display_id = mobj.group('display_id')
|
||||
webpage = self._download_webpage(url, display_id or short_id)
|
||||
real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id')
|
||||
|
||||
video_info = self.download_video_info(real_id)
|
||||
|
||||
error_desc = video_info.get('error_desc')
|
||||
if error_desc:
|
||||
raise ExtractorError(
|
||||
'%s returned error: %s' % (self.IE_NAME, error_desc), expected=True)
|
||||
|
||||
geo_list = video_info.get('geoList')
|
||||
country = geo_list[0] if geo_list else ''
|
||||
|
||||
chapters = video_info['chapters']
|
||||
first_chapter = chapters[0]
|
||||
files = video_info['files']
|
||||
first_file = files[0]
|
||||
|
||||
if real_id_for_chapter(first_chapter) != real_id:
|
||||
self.to_screen('Multipart video detected')
|
||||
chapter_urls = []
|
||||
for chapter in chapters:
|
||||
chapter_id = real_id_for_chapter(chapter)
|
||||
# Yes, when we this chapter is processed by WatIE,
|
||||
# it will download the info again
|
||||
chapter_info = self.download_video_info(chapter_id)
|
||||
chapter_urls.append(chapter_info['url'])
|
||||
entries = [self.url_result(chapter_url) for chapter_url in chapter_urls]
|
||||
return self.playlist_result(entries, real_id, video_info['title'])
|
||||
|
||||
upload_date = None
|
||||
if 'date_diffusion' in first_chapter:
|
||||
upload_date = unified_strdate(first_chapter['date_diffusion'])
|
||||
# Otherwise we can continue and extract just one part, we have to use
|
||||
# the short id for getting the video url
|
||||
|
||||
formats = [{
|
||||
'url': 'http://wat.tv/get/android5/%s.mp4' % real_id,
|
||||
'format_id': 'Mobile',
|
||||
}]
|
||||
|
||||
fmts = [('SD', 'web')]
|
||||
if first_file.get('hasHD'):
|
||||
fmts.append(('HD', 'webhd'))
|
||||
|
||||
def compute_token(param):
|
||||
timestamp = '%08x' % int(self._download_webpage(
|
||||
'http://www.wat.tv/servertime', real_id,
|
||||
'Downloading server time').split('|')[0])
|
||||
magic = '9b673b13fa4682ed14c3cfa5af5310274b514c4133e9b3a81e6e3aba009l2564'
|
||||
return '%s/%s' % (hashlib.md5((magic + param + timestamp).encode('ascii')).hexdigest(), timestamp)
|
||||
|
||||
for fmt in fmts:
|
||||
webid = '/%s/%s' % (fmt[1], real_id)
|
||||
video_url = self._download_webpage(
|
||||
'http://www.wat.tv/get%s?token=%s&getURL=1&country=%s' % (webid, compute_token(webid), country),
|
||||
real_id,
|
||||
'Downloading %s video URL' % fmt[0],
|
||||
'Failed to download %s video URL' % fmt[0],
|
||||
False)
|
||||
if not video_url:
|
||||
continue
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'ext': 'mp4',
|
||||
'format_id': fmt[0],
|
||||
})
|
||||
|
||||
return {
|
||||
'id': real_id,
|
||||
'display_id': display_id,
|
||||
'title': first_chapter['title'],
|
||||
'thumbnail': first_chapter['preview'],
|
||||
'description': first_chapter['description'],
|
||||
'view_count': video_info['views'],
|
||||
'upload_date': upload_date,
|
||||
'duration': first_file['duration'],
|
||||
'formats': formats,
|
||||
}
|
||||
Loading…
x
Reference in New Issue
Block a user