X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Fpatreon.py;h=5429592a75a9f66fdc9f0e9fb908af9e67559aae;hb=191b7cbba95679b389a509420993af56ef51545d;hp=da1ad065a15f7b55fd0a697b278fea2961b02e71;hpb=a00d73c8c8fe1c33053ccc102153c13ead1614ec;p=youtube-dl diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py index da1ad065a..5429592a7 100644 --- a/youtube_dl/extractor/patreon.py +++ b/youtube_dl/extractor/patreon.py @@ -1,79 +1,38 @@ # encoding: utf-8 from __future__ import unicode_literals +import json import re from .common import InfoExtractor from ..utils import ( - ExtractorError, - compat_html_parser, - #compat_urllib_request, - #compat_urllib_parse, + js_to_json, ) -class PatreonHTMLParser(compat_html_parser.HTMLParser): - _PREFIX = 'http://www.patreon.com' - _ATTACH_TAGS = 5 * ['div'] - _ATTACH_CLASSES = [ - 'fancyboxhidden', 'box photo double', 'boxwrapper double', - 'hiddendisplay shareinfo', 'attach' - ] - _INFO_TAGS = 4 * ['div'] - _INFO_CLASSES = [ - 'fancyboxhidden', 'box photo double', 'boxwrapper double', - 'hiddendisplay shareinfo' - ] - - def get_creation_info(self, html_data): - self.tag_stack = [] - self.attrs_stack = [] - self.creation_info = {} - self.feed(html_data) - - def handle_starttag(self, tag, attrs): - self.tag_stack.append(tag.lower()) - self.attrs_stack.append(dict(attrs)) - - def handle_endtag(self, tag): - self.tag_stack.pop() - self.attrs_stack.pop() - - def handle_data(self, data): - # Check first if this is a creation attachment - if self.tag_stack[-6:-1] == self._ATTACH_TAGS: - attrs_classes = [ - x.get('class', '').lower() for x in self.attrs_stack[-6:-1] - ] - if attrs_classes == self._ATTACH_CLASSES: - if self.tag_stack[-1] == 'a': - url = self._PREFIX + self.attrs_stack[-1].get('href') - self.creation_info['url'] = url - if '.' in data: - self.creation_info['ext'] = data.rsplit('.')[-1] - # Next, check if this is within the div containing the creation info - if self.tag_stack[-5:-1] == self._INFO_TAGS: - attrs_classes = [ - x.get('class', '').lower() for x in self.attrs_stack[-5:-1] - ] - if attrs_classes == self._INFO_CLASSES: - if self.attrs_stack[-1].get('class') == 'utitle': - self.creation_info['title'] = data.strip() - - class PatreonIE(InfoExtractor): - IE_NAME = 'patreon' _VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(.+)' _TESTS = [ { 'url': 'http://www.patreon.com/creation?hid=743933', 'md5': 'e25505eec1053a6e6813b8ed369875cc', - 'name': 'Patreon', 'info_dict': { 'id': '743933', 'ext': 'mp3', 'title': 'Episode 166: David Smalley of Dogma Debate', 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', + }, + }, + { + 'url': 'http://www.patreon.com/creation?hid=754133', + 'md5': '3eb09345bf44bf60451b8b0b81759d0a', + 'info_dict': { + 'id': '754133', + 'ext': 'mp3', + 'title': 'CD 167 Extra', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', }, }, ] @@ -109,19 +68,33 @@ class PatreonIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group(1) - info_page = self._download_webpage(url, video_id) - - ret = {'id': video_id} - try: - ret['uploader'] = re.search( - r'(.+) is creating', info_page - ).group(1) - except AttributeError: - pass - - parser = PatreonHTMLParser() - parser.get_creation_info(info_page) - if not parser.creation_info.get('url'): - raise ExtractionError('Unable to retrieve creation URL') - ret.update(parser.creation_info) - return ret + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage).strip() + + attach_fn = self._html_search_regex( + r'