From 355e41466d8edcb5b2457dfa0c5715ef87ff5832 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 29 Dec 2014 21:33:41 +0600 Subject: [PATCH] [hellporno] Extract all formats and improve --- youtube_dl/extractor/hellporno.py | 47 ++++++++++++++++++++++--------- 1 file changed, 33 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py index 754322cdf..7a1c75b65 100644 --- a/youtube_dl/extractor/hellporno.py +++ b/youtube_dl/extractor/hellporno.py @@ -1,5 +1,12 @@ from __future__ import unicode_literals + +import re + from .common import InfoExtractor +from ..utils import ( + js_to_json, + remove_end, +) class HellPornoIE(InfoExtractor): @@ -19,23 +26,36 @@ class HellPornoIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - video_id = self._html_search_regex( - r'video_id:\s*\'([^\']+)\'', webpage, 'id') + 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') - video_url = self._html_search_regex( - r'video_url:\s*\'([^\']+)\'', webpage, 'video_url') + flashvars = self._parse_json(self._search_regex( + r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'), + display_id, transform_source=js_to_json) - title = self._html_search_regex( - r'([^<]+)\s*-\s*Hell Porno', webpage, 'title') + video_id = flashvars.get('video_id') + thumbnail = flashvars.get('preview_url') + ext = flashvars.get('postfix', '.mp4')[1:] - 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 = self._html_search_meta( 'keywords', webpage, 'categories', default='').split(',') @@ -43,10 +63,9 @@ class HellPornoIE(InfoExtractor): return { 'id': video_id, 'display_id': display_id, - 'url': video_url, 'title': title, - 'ext': ext, 'thumbnail': thumbnail, 'categories': categories, 'age_limit': 18, + 'formats': formats, }