1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-22 19:52:53 +08:00
youtube-dl/youtube_dl/extractor/patreon.py
2018-10-05 22:45:04 +01:00

137 lines
4.5 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
determine_ext,
int_or_none,
parse_iso8601,
)
class PatreonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?patreon\.com/(?:creation\?hid=|posts/(?:[\w-]+-)?)(?P<id>\d+)'
_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',
'description': 'md5:713b08b772cd6271b9f3906683cfacdf',
'uploader': 'Cognitive Dissonance Podcast',
'thumbnail': 're:^https?://.*$',
'timestamp': 1406473987,
'upload_date': '20140727',
},
}, {
'url': 'http://www.patreon.com/creation?hid=754133',
'md5': '3eb09345bf44bf60451b8b0b81759d0a',
'info_dict': {
'id': '754133',
'ext': 'mp3',
'title': 'CD 167 Extra',
'uploader': 'Cognitive Dissonance Podcast',
'thumbnail': 're:^https?://.*$',
},
'skip': 'Patron-only content',
}, {
'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,
}
}, {
'url': 'https://www.patreon.com/posts/episode-166-of-743933',
'only_matching': True,
}, {
'url': 'https://www.patreon.com/posts/743933',
'only_matching': 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')
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)
post = self._download_json(
'https://www.patreon.com/api/posts/' + video_id, video_id)
attributes = post['data']['attributes']
title = attributes['title'].strip()
image = attributes.get('image') or {}
info = {
'id': video_id,
'title': title,
'description': clean_html(attributes.get('content')),
'thumbnail': image.get('large_url') or image.get('url'),
'timestamp': parse_iso8601(attributes.get('published_at')),
'like_count': int_or_none(attributes.get('like_count')),
'comment_count': int_or_none(attributes.get('comment_count')),
}
def add_file(file_data):
file_url = file_data.get('url')
if file_url:
info.update({
'url': file_url,
'ext': determine_ext(file_data.get('name'), 'mp3'),
})
for i in post.get('included', []):
i_type = i.get('type')
if i_type == 'attachment':
add_file(i.get('attributes') or {})
elif i_type == 'user':
user_attributes = i.get('attributes')
if user_attributes:
info.update({
'uploader': user_attributes.get('full_name'),
'uploader_url': user_attributes.get('url'),
})
if not info.get('url'):
add_file(attributes.get('post_file') or {})
if not info.get('url'):
info.update({
'_type': 'url',
'url': attributes['embed']['url'],
})
return info