From 7881a6449901d2cf22b58c00ff057a979f6d2e2a Mon Sep 17 00:00:00 2001 From: pulpe Date: Tue, 4 Feb 2014 07:45:41 +0100 Subject: [PATCH] [iprima] Add support for play.iprima.cz --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/iprima.py | 83 ++++++++++++++++++++++++++++++++ 2 files changed, 84 insertions(+) create mode 100644 youtube_dl/extractor/iprima.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 073f3a0d14..a8d5a9cb82 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -96,6 +96,7 @@ from .ina import InaIE from .infoq import InfoQIE from .instagram import InstagramIE from .internetvideoarchive import InternetVideoArchiveIE +from .iprima import IPrimaIE from .ivi import ( IviIE, IviCompilationIE diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py new file mode 100644 index 0000000000..95557ff10d --- /dev/null +++ b/youtube_dl/extractor/iprima.py @@ -0,0 +1,83 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re +from random import random +from math import floor + +from .common import InfoExtractor +from ..utils import compat_urllib_request + + +class IPrimaIE(InfoExtractor): + _VALID_URL = r'https?://play\.iprima\.cz/(?P.+)/(?P.+)' + + _TESTS = [{ + 'url': 'http://play.iprima.cz/particka/particka-92', + 'info_dict': { + 'id': '39152', + 'ext': 'flv', + 'title': 'Partička (92)', + 'description': 'md5:3740fda51464da35a2d4d0670b8e4fd6', + 'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg', + }, + 'params': { + 'skip_download': True, + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('videoid') + + webpage = self._download_webpage(url, video_id) + + player_url = 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % ( + floor(random()*1073741824), + floor(random()*1073741824)) + + req = compat_urllib_request.Request(player_url) + req.add_header('Referer', url) + playerpage = self._download_webpage(req, video_id) + + base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1]) + + zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO') + + if zoneGEO != '0': + base_url = base_url.replace('token', 'token_'+zoneGEO) + + formats = [] + for format_id in ['lq', 'hq', 'hd']: + filename = self._html_search_regex(r'"%s_id":(.+?),' % format_id, webpage, 'filename') + + if filename == 'null': + continue + + real_id = self._search_regex(r'Prima-[0-9]{10}-([0-9]+)_', filename, 'real video id') + + if format_id == 'lq': + quality = 0 + elif format_id == 'hq': + quality = 1 + elif format_id == 'hd': + quality = 2 + filename = 'hq/'+filename + + formats.append({ + 'format_id': format_id, + 'url': base_url, + 'quality': quality, + 'play_path': 'mp4:'+filename.replace('"', '')[:-4], + 'rtmp_live': True, + 'ext': 'flv', + }) + + return { + 'id': real_id, + 'title': self._og_search_title(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'formats': formats, + 'description': self._og_search_description(webpage), + } \ No newline at end of file