X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fhellporno.py;h=0ee8ea712c72e618a4d7544f26c376e94fcaf70d;hb=56667d622c3f6e7594a04f8cd5f4371875940725;hp=06f85127f206fb6303a6a1a112e4f38d166cbea3;hpb=6a1c4fbfcb57c138b8ace305127c2654844e8099;p=youtube-dl diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py index 06f85127f..0ee8ea712 100644 --- a/youtube_dl/extractor/hellporno.py +++ b/youtube_dl/extractor/hellporno.py @@ -3,54 +3,73 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import ( + js_to_json, + remove_end, + determine_ext, +) + class HellPornoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P[^/]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P[^/]+)' + _TESTS = [{ 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/', 'md5': '1fee339c610d2049699ef2aa699439f1', 'info_dict': { 'id': '149116', + 'display_id': 'dixie-is-posing-with-naked-ass-very-erotic', 'ext': 'mp4', 'title': 'Dixie is posing with naked ass very erotic', - 'description': 'md5:5ba02cbf31eff820147b3cc25306d89a', - 'categories': list, # NSFW - 'thumbnail': 're:https?://.*\.jpg$', + 'thumbnail': r're:https?://.*\.jpg$', 'age_limit': 18, } - } + }, { + 'url': 'http://hellporno.net/v/186271/', + 'only_matching': True, + }] def _real_extract(self, url): - webpage = self._download_webpage(url, 'main') - - video_id = self._html_search_regex(r'video_id:\s*\'([^\']+)\'', webpage, 'id') + display_id = self._match_id(url) - video_url = self._html_search_regex(r'video_url:\s*\'([^\']+)\'', webpage, 'video_url') + webpage = self._download_webpage(url, display_id) - ext = self._html_search_regex(r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:] + title = remove_end(self._html_search_regex( + r'([^<]+)', webpage, 'title'), ' - Hell Porno') - title = self._html_search_regex( - r'([^<]+)\s*-\s*Hell Porno', webpage, 'title') + flashvars = self._parse_json(self._search_regex( + r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'), + display_id, transform_source=js_to_json) - description = self._html_search_meta('description', webpage, 'description', fatal=False) + video_id = flashvars.get('video_id') + thumbnail = flashvars.get('preview_url') + ext = determine_ext(flashvars.get('postfix'), 'mp4') - thumbnail = self._html_search_regex( - r'preview_url:\s*\'([^\']+)\'', - webpage, 'thumbnail', fatal=False) + formats = [] + for video_url_key in ['video_url', 'video_alt_url']: + video_url = flashvars.get(video_url_key) + if not video_url: + continue + video_text = flashvars.get('%s_text' % video_url_key) + fmt = { + 'url': video_url, + 'ext': ext, + 'format_id': video_text, + } + m = re.search(r'^(?P\d+)[pP]', video_text) + if m: + fmt['height'] = int(m.group('height')) + formats.append(fmt) + self._sort_formats(formats) - categories_str = self._html_search_regex( - r'