From 5aa38e75b27b428b67f9f7083c44051881c98fd8 Mon Sep 17 00:00:00 2001 From: Carlos Ramos Date: Fri, 19 Sep 2014 22:46:57 +0200 Subject: [PATCH] [played] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/played.py | 57 ++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) create mode 100644 youtube_dl/extractor/played.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 625666acbe..9ee3f9190e 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -266,6 +266,7 @@ from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE from .pbs import PBSIE from .photobucket import PhotobucketIE +from .played import PlayedIE from .playfm import PlayFMIE from .playvid import PlayvidIE from .podomatic import PodomaticIE diff --git a/youtube_dl/extractor/played.py b/youtube_dl/extractor/played.py new file mode 100644 index 0000000000..a396e62e50 --- /dev/null +++ b/youtube_dl/extractor/played.py @@ -0,0 +1,57 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import time +import os.path + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, +) + + +class PlayedIE(InfoExtractor): + IE_NAME = 'played.to' + _VALID_URL = r'https?://played\.to/(?P[a-zA-Z0-9_-]+)' + + _TEST = { + 'url': 'http://played.to/j2f2sfiiukgt', + 'md5': 'c2bd75a368e82980e7257bf500c00637', + 'info_dict': { + 'id': 'j2f2sfiiukgt', + 'ext': 'flv', + 'title': 'youtube-dl_test_video.mp4', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + orig_webpage = self._download_webpage(url, video_id) + fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage) + data = dict(fields) + + self.to_screen('%s: Waiting for timeout' % video_id) + time.sleep(2) + + post = compat_urllib_parse.urlencode(data) + headers = { + b'Content-Type': b'application/x-www-form-urlencoded', + } + req = compat_urllib_request.Request(url, post, headers) + webpage = self._download_webpage( + req, video_id, note='Downloading video page ...') + + title = os.path.splitext(data['fname'])[0] + + video_url = self._search_regex( + r'file: "?(.+?)",', webpage, 'video URL') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + } \ No newline at end of file