From e0942e37aa6f20de88f6d5ed7dc288408500371a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 18 Jul 2014 21:39:21 +0700 Subject: [PATCH] [crackled] Improve, fix invalid regexes and extract more metadata --- youtube_dl/extractor/cracked.py | 61 +++++++++++++++++++++------------ 1 file changed, 40 insertions(+), 21 deletions(-) diff --git a/youtube_dl/extractor/cracked.py b/youtube_dl/extractor/cracked.py index 37c0f7ffb..74b880ffc 100644 --- a/youtube_dl/extractor/cracked.py +++ b/youtube_dl/extractor/cracked.py @@ -1,23 +1,26 @@ -# coding: utf-8 from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + str_to_int, +) + class CrackedIE(InfoExtractor): - _VALID_URL = r'http?://.*?\.cracked\.com/video_+(?P.*)_.*' + _VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P\d+)_[\da-z-]+\.html' _TEST = { - 'url': 'http://www.cracked.com/video_18803_4-social-criticisms-hidden-in-sonic-hedgehog-games.html', - + 'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html', + 'md5': '4b29a5eeec292cd5eca6388c7558db9e', 'info_dict': { - 'id': '18803', + 'id': '19006', 'ext': 'mp4', - 'title': "4 Social Criticisms Hidden in 'Sonic the Hedgehog' Games | Cracked.com", - 'height': 375, - 'width': 666, - - + 'title': '4 Plot Holes You Didn\'t Notice in Your Favorite Movies', + 'description': 'md5:3b909e752661db86007d10e5ec2df769', + 'timestamp': 1405659600, + 'upload_date': '20140718', } } @@ -26,21 +29,37 @@ def _real_extract(self, url): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - title = self._search_regex(r'(.*?)',webpage,'title') - video_url = self._search_regex(r'var CK_vidSrc = "+(.*)"',webpage,'url') - width = self._search_regex(r'width="(.*?)"',webpage,'width') - height = re.findall(r'height="(.*?)"',webpage)[1] + video_url = self._html_search_regex( + [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'([\d,\.]+) Views', webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'([\d,\.]+)', webpage, 'comment count', fatal=False)) + + m = re.search(r'_(?P\d+)X(?P\d+)\.mp4$', video_url) + if m: + width = int(m.group('width')) + height = int(m.group('height')) + else: + width = height = None return { - 'url':video_url, 'id': video_id, - 'ext':'mp4', - 'title':title, - 'height':int(height), - 'width':int(width) - - + 'url':video_url, + 'title': title, + 'description': description, + 'timestamp': timestamp, + 'view_count': view_count, + 'comment_count': comment_count, + 'height': height, + 'width': width, } \ No newline at end of file