1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-21 15:32:51 +08:00
youtube-dl/youtube_dl/extractor/patreon.py

118 lines
4.1 KiB
Python
Raw Normal View History

2014-07-29 02:40:58 +08:00
# encoding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
2014-08-22 08:33:29 +08:00
js_to_json,
2014-07-29 02:40:58 +08:00
)
class PatreonIE(InfoExtractor):
2015-02-19 07:38:05 +08:00
_VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(?P<id>[^&#]+)'
2014-07-29 02:40:58 +08:00
_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',
2014-08-22 08:33:29 +08:00
'thumbnail': 're:^https?://.*$',
2014-07-29 02:40:58 +08:00
},
},
{
'url': 'http://www.patreon.com/creation?hid=754133',
'md5': '3eb09345bf44bf60451b8b0b81759d0a',
'info_dict': {
'id': '754133',
'ext': 'mp3',
'title': 'CD 167 Extra',
'uploader': 'Cognitive Dissonance Podcast',
2014-08-22 08:33:29 +08:00
'thumbnail': 're:^https?://.*$',
},
},
{
'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,
}
}
2014-07-29 02:40:58 +08:00
]
# 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 = compat_urllib_request.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):
2015-02-19 07:38:05 +08:00
video_id = self._match_id(url)
2014-08-22 08:33:29 +08:00
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)
2014-08-22 08:33:29 +08:00
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)
2014-08-22 08:33:29 +08:00
else:
2015-02-19 07:38:05 +08:00
playlist = self._parse_json(self._search_regex(
2014-08-22 08:33:29 +08:00
r'(?s)new\s+jPlayerPlaylist\(\s*\{\s*[^}]*},\s*(\[.*?,?\s*\])',
2015-02-19 07:38:05 +08:00
webpage, 'playlist JSON'),
video_id, transform_source=js_to_json)
2014-08-22 08:33:29 +08:00
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,
}