X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/848723ea972c09f28787db91d8c06e98a274ab89..a5a28b1eabe0533f26d23c4157c97144215b22b7:/youtube_dl/extractor/cliphunter.py?ds=sidebyside diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index 58846e8..ab651d1 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -1,11 +1,10 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..utils import int_or_none -translation_table = { +_translation_table = { 'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n', 'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r', 'y': 'l', 'z': 'i', @@ -13,44 +12,77 @@ translation_table = { } +def _decode(s): + return ''.join(_translation_table.get(c, c) for c in s) + + class CliphunterIE(InfoExtractor): IE_NAME = 'cliphunter' - _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/ + _VALID_URL = r'''(?x)https?://(?:www\.)?cliphunter\.com/w/ (?P[0-9]+)/ (?P.+?)(?:$|[#\?]) ''' - _TEST = { + _TESTS = [{ 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', - 'file': '1012420.flv', - 'md5': '15e7740f30428abf70f4223478dc1225', + 'md5': 'b7c9bbd4eb3a226ab91093714dcaa480', 'info_dict': { + 'id': '1012420', + 'ext': 'flv', 'title': 'Fun Jynx Maze solo', - } - } + 'thumbnail': r're:^https?://.*\.jpg$', + 'age_limit': 18, + }, + 'skip': 'Video gone', + }, { + 'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz', + 'md5': '55a723c67bfc6da6b0cfa00d55da8a27', + 'info_dict': { + 'id': '2019449', + 'ext': 'mp4', + 'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz', + 'thumbnail': r're:^https?://.*\.jpg$', + 'age_limit': 18, + }, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - pl_fiji = self._search_regex( - r'pl_fiji = \'([^\']+)\'', webpage, 'video data') - pl_c_qual = self._search_regex( - r'pl_c_qual = "(.)"', webpage, 'video quality') video_title = self._search_regex( r'mediaTitle = "([^"]+)"', webpage, 'title') - video_url = ''.join(translation_table.get(c, c) for c in pl_fiji) + gexo_files = self._parse_json( + self._search_regex( + r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'), + video_id) + + formats = [] + for format_id, f in gexo_files.items(): + video_url = f.get('url') + if not video_url: + continue + fmt = f.get('fmt') + height = f.get('h') + format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id + formats.append({ + 'url': _decode(video_url), + 'format_id': format_id, + 'width': int_or_none(f.get('w')), + 'height': int_or_none(height), + 'tbr': int_or_none(f.get('br')), + }) + self._sort_formats(formats) - formats = [{ - 'url': video_url, - 'format_id': pl_c_qual, - }] + thumbnail = self._search_regex( + r"var\s+mov_thumb\s*=\s*'([^']+)';", + webpage, 'thumbnail', fatal=False) return { 'id': video_id, 'title': video_title, 'formats': formats, + 'age_limit': self._rta_search(webpage), + 'thumbnail': thumbnail, }