from __future__ import unicode_literals import re from .common import InfoExtractor from ..compat import ( compat_urllib_parse, compat_urllib_request, ) from ..utils import ExtractorError class PrimeShareTVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?primeshare\.tv/download/(?P[\da-zA-Z]+)' _TEST = { 'url': 'http://primeshare.tv/download/238790B611', 'md5': 'b92d9bf5461137c36228009f31533fbc', 'info_dict': { 'id': '238790B611', 'ext': 'mp4', 'title': 'Public Domain - 1960s Commercial - Crest Toothpaste-YKsuFona', }, } def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) if '>File not exist<' in webpage: raise ExtractorError('Video %s does not exist' % video_id, expected=True) fields = dict(re.findall(r'''(?x)Watch\s*(?: )?\s*\((.+?)(?:\s*\[\.\.\.\])?\)\s*(?: )?\s*', video_page, 'title') return { 'id': video_id, 'url': video_url, 'title': title, 'ext': 'mp4', }