From 8e72edfb19b5f6f87210f62f02fe876789641dbe Mon Sep 17 00:00:00 2001 From: Naglis Jonaitis Date: Fri, 29 Aug 2014 00:20:10 +0300 Subject: [PATCH] [promptfile] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/promptfile.py | 67 ++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+) create mode 100644 youtube_dl/extractor/promptfile.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 17ed69ba4..1479d998a 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -257,6 +257,7 @@ from .podomatic import PodomaticIE from .pornhd import PornHdIE from .pornhub import PornHubIE from .pornotube import PornotubeIE +from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE from .pyvideo import PyvideoIE from .radiofrance import RadioFranceIE diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py new file mode 100644 index 000000000..9ef49b19a --- /dev/null +++ b/youtube_dl/extractor/promptfile.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + determine_ext, + compat_urllib_parse, + compat_urllib_request, +) + + +class PromptFileIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P[0-9A-Z\-]+)' + _FILE_NOT_FOUND_REGEX = r'.+[^-]' + _TEST = { + 'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF', + 'md5': 'd1451b6302da7215485837aaea882c4c', + 'info_dict': { + 'id': 'D21B4746E9-F01462F0FF', + 'ext': 'mp4', + 'title': 'Birds.mp4', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None: + 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') + webpage = self._download_webpage( + req, video_id, 'Downloading video page') + + url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL') + title = self._html_search_regex( + r'', webpage, 'title') + thumbnail = self._html_search_regex( + r'
.*button>.*?