X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/ced7488f6d3a519b2c1b1cbd31048743fb8285bd..e96056e11025aad125c364bd96b2a2df071dd2ae:/youtube_dl/extractor/vidzi.py diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py index d49cc6c..42ea495 100644 --- a/youtube_dl/extractor/vidzi.py +++ b/youtube_dl/extractor/vidzi.py @@ -1,15 +1,19 @@ # coding: utf-8 from __future__ import unicode_literals -from .jwplatform import JWPlatformBaseIE +import re + +from .common import InfoExtractor from ..utils import ( decode_packed_codes, js_to_json, + NO_DEFAULT, + PACKED_CODES_RE, ) -class VidziIE(JWPlatformBaseIE): - _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?:embed-)?(?P[0-9a-zA-Z]+)' +class VidziIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc|si|nu)/(?:embed-)?(?P[0-9a-zA-Z]+)' _TESTS = [{ 'url': 'http://vidzi.tv/cghql9yq6emu.html', 'md5': '4f16c71ca0c8c8635ab6932b5f3f1660', @@ -24,7 +28,16 @@ class VidziIE(JWPlatformBaseIE): }, }, { 'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html', - 'skip_download': True, + 'only_matching': True, + }, { + 'url': 'http://vidzi.cc/cghql9yq6emu.html', + 'only_matching': True, + }, { + 'url': 'https://vidzi.si/rph9gztxj1et.html', + 'only_matching': True, + }, { + 'url': 'http://vidzi.nu/cghql9yq6emu.html', + 'only_matching': True, }] def _real_extract(self, url): @@ -35,10 +48,19 @@ class VidziIE(JWPlatformBaseIE): title = self._html_search_regex( r'(?s)

(.*?)

', webpage, 'title') - code = decode_packed_codes(webpage).replace('\\\'', '\'') - jwplayer_data = self._parse_json( - self._search_regex(r'setup\(([^)]+)\)', code, 'jwplayer data'), - video_id, transform_source=js_to_json) + codes = [webpage] + codes.extend([ + decode_packed_codes(mobj.group(0)).replace('\\\'', '\'') + for mobj in re.finditer(PACKED_CODES_RE, webpage)]) + for num, code in enumerate(codes, 1): + jwplayer_data = self._parse_json( + self._search_regex( + r'setup\(([^)]+)\)', code, 'jwplayer data', + default=NO_DEFAULT if num == len(codes) else '{}'), + video_id, transform_source=lambda s: js_to_json( + re.sub(r'\s*\+\s*window\[.+?\]', '', s))) + if jwplayer_data: + break info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False) info_dict['title'] = title