mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-05 07:53:18 +00:00
5c2266df4b
compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
116 lines
4 KiB
Python
116 lines
4 KiB
Python
# encoding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import js_to_json
|
|
|
|
|
|
class PatreonIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(?P<id>[^&#]+)'
|
|
_TESTS = [
|
|
{
|
|
'url': 'http://www.patreon.com/creation?hid=743933',
|
|
'md5': 'e25505eec1053a6e6813b8ed369875cc',
|
|
'info_dict': {
|
|
'id': '743933',
|
|
'ext': 'mp3',
|
|
'title': 'Episode 166: David Smalley of Dogma Debate',
|
|
'uploader': 'Cognitive Dissonance Podcast',
|
|
'thumbnail': 're:^https?://.*$',
|
|
},
|
|
},
|
|
{
|
|
'url': 'http://www.patreon.com/creation?hid=754133',
|
|
'md5': '3eb09345bf44bf60451b8b0b81759d0a',
|
|
'info_dict': {
|
|
'id': '754133',
|
|
'ext': 'mp3',
|
|
'title': 'CD 167 Extra',
|
|
'uploader': 'Cognitive Dissonance Podcast',
|
|
'thumbnail': 're:^https?://.*$',
|
|
},
|
|
},
|
|
{
|
|
'url': 'https://www.patreon.com/creation?hid=1682498',
|
|
'info_dict': {
|
|
'id': 'SU4fj_aEMVw',
|
|
'ext': 'mp4',
|
|
'title': 'I\'m on Patreon!',
|
|
'uploader': 'TraciJHines',
|
|
'thumbnail': 're:^https?://.*$',
|
|
'upload_date': '20150211',
|
|
'description': 'md5:c5a706b1f687817a3de09db1eb93acd4',
|
|
'uploader_id': 'TraciJHines',
|
|
},
|
|
'params': {
|
|
'noplaylist': True,
|
|
'skip_download': True,
|
|
}
|
|
}
|
|
]
|
|
|
|
# Currently Patreon exposes download URL via hidden CSS, so login is not
|
|
# needed. Keeping this commented for when this inevitably changes.
|
|
'''
|
|
def _login(self):
|
|
(username, password) = self._get_login_info()
|
|
if username is None:
|
|
return
|
|
|
|
login_form = {
|
|
'redirectUrl': 'http://www.patreon.com/',
|
|
'email': username,
|
|
'password': password,
|
|
}
|
|
|
|
request = sanitized_Request(
|
|
'https://www.patreon.com/processLogin',
|
|
compat_urllib_parse.urlencode(login_form).encode('utf-8')
|
|
)
|
|
login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
|
|
|
|
if re.search(r'onLoginFailed', login_page):
|
|
raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
|
|
|
|
def _real_initialize(self):
|
|
self._login()
|
|
'''
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
webpage = self._download_webpage(url, video_id)
|
|
title = self._og_search_title(webpage).strip()
|
|
|
|
attach_fn = self._html_search_regex(
|
|
r'<div class="attach"><a target="_blank" href="([^"]+)">',
|
|
webpage, 'attachment URL', default=None)
|
|
embed = self._html_search_regex(
|
|
r'<div[^>]+id="watchCreation"[^>]*>\s*<iframe[^>]+src="([^"]+)"',
|
|
webpage, 'embedded URL', default=None)
|
|
|
|
if attach_fn is not None:
|
|
video_url = 'http://www.patreon.com' + attach_fn
|
|
thumbnail = self._og_search_thumbnail(webpage)
|
|
uploader = self._html_search_regex(
|
|
r'<strong>(.*?)</strong> is creating', webpage, 'uploader')
|
|
elif embed is not None:
|
|
return self.url_result(embed)
|
|
else:
|
|
playlist = self._parse_json(self._search_regex(
|
|
r'(?s)new\s+jPlayerPlaylist\(\s*\{\s*[^}]*},\s*(\[.*?,?\s*\])',
|
|
webpage, 'playlist JSON'),
|
|
video_id, transform_source=js_to_json)
|
|
data = playlist[0]
|
|
video_url = self._proto_relative_url(data['mp3'])
|
|
thumbnail = self._proto_relative_url(data.get('cover'))
|
|
uploader = data.get('artist')
|
|
|
|
return {
|
|
'id': video_id,
|
|
'url': video_url,
|
|
'ext': 'mp3',
|
|
'title': title,
|
|
'uploader': uploader,
|
|
'thumbnail': thumbnail,
|
|
}
|