X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a070911bf98c751e4425008f1335cc57c86d30fc..d037080638e8dbb0ebb2ac9cf23b9671518340f9:/youtube_dl/extractor/promptfile.py?ds=sidebyside diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py index f536e6e..23ac93d 100644 --- a/youtube_dl/extractor/promptfile.py +++ b/youtube_dl/extractor/promptfile.py @@ -4,26 +4,23 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) from ..utils import ( determine_ext, ExtractorError, + urlencode_postdata, ) class PromptFileIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P[0-9A-Z\-]+)' _TEST = { - 'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF', - 'md5': 'd1451b6302da7215485837aaea882c4c', + 'url': 'http://www.promptfile.com/l/86D1CE8462-576CAAE416', + 'md5': '5a7e285a26e0d66d9a263fae91bc92ce', 'info_dict': { - 'id': 'D21B4746E9-F01462F0FF', + 'id': '86D1CE8462-576CAAE416', 'ext': 'mp4', - 'title': 'Birds.mp4', - 'thumbnail': 're:^https?://.*\.jpg$', + 'title': 'oceans.mp4', + 'thumbnail': r're:^https?://.*\.jpg$', } } @@ -35,17 +32,23 @@ class PromptFileIE(InfoExtractor): raise ExtractorError('Video %s does not exist' % video_id, expected=True) - fields = dict(re.findall(r'''(?x)type="hidden"\s+ - name="(.+?)"\s+ - value="(.*?)" - ''', webpage)) - post = compat_urllib_parse.urlencode(fields) - req = compat_urllib_request.Request(url, post) - req.add_header('Content-type', 'application/x-www-form-urlencoded') + chash = self._search_regex( + r'val\("([^"]*)"\s*\+\s*\$\("#chash"\)', webpage, 'chash') + fields = self._hidden_inputs(webpage) + keys = list(fields.keys()) + chash_key = keys[0] if len(keys) == 1 else next( + key for key in keys if key.startswith('cha')) + fields[chash_key] = chash + fields[chash_key] + webpage = self._download_webpage( - req, video_id, 'Downloading video page') + url, video_id, 'Downloading video page', + data=urlencode_postdata(fields), + headers={'Content-type': 'application/x-www-form-urlencoded'}) - url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL') + video_url = self._search_regex( + (r']+href=(["\'])(?P(?:(?!\1).)+)\1[^>]*>\s*Download File', + r']+href=(["\'])(?Phttps?://(?:www\.)?promptfile\.com/file/(?:(?!\1).)+)\1'), + webpage, 'video url', group='url') title = self._html_search_regex( r'', webpage, 'title') thumbnail = self._html_search_regex( @@ -54,7 +57,7 @@ class PromptFileIE(InfoExtractor): formats = [{ 'format_id': 'sd', - 'url': url, + 'url': video_url, 'ext': determine_ext(title), }] self._sort_formats(formats)