From bfe96d7bea7c5227456bf1aecca51907c8f30c51 Mon Sep 17 00:00:00 2001 From: Philip Huppert Date: Fri, 9 Oct 2015 18:38:11 +0200 Subject: [PATCH] [presstv] Added extractor PressTV. Fixes #7060 --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/presstv.py | 80 ++++++++++++++++++++++++++++++ 2 files changed, 81 insertions(+) create mode 100644 youtube_dl/extractor/presstv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index de29c7956f..c2fa83918f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -583,6 +583,7 @@ from .pornotube import PornotubeIE from .pornovoisines import PornoVoisinesIE from .pornoxo import PornoXOIE +from .presstv import PressTVIE from .primesharetv import PrimeShareTVIE from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE diff --git a/youtube_dl/extractor/presstv.py b/youtube_dl/extractor/presstv.py new file mode 100644 index 0000000000..724d8b1c43 --- /dev/null +++ b/youtube_dl/extractor/presstv.py @@ -0,0 +1,80 @@ +# coding: utf-8 +from __future__ import unicode_literals +import re + +from .common import InfoExtractor +from ..utils import str_to_int + + +class PressTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?presstv\.ir/Video/(?P[0-9]+)/(?P[0-9]+)/(?P[0-9]+)/(?P[0-9]+)/' + + _TEST = { + 'url': 'http://www.presstv.ir/Video/2015/10/04/431915/Max-Igan-Press-TV-Face-to-Face', + 'md5': 'e95736ac75088b5f1e5bbb68f248f90d', + 'info_dict': { + 'id': '431915', + 'ext': 'mp4', + 'title': 'Press TV’s full interview with Max Igan', + 'upload_date': '20151004', + 'thumbnail': 'http://217.218.67.233/photo/20151004/d5c333ad-98f9-4bd3-bc3e-a1ad6a192803.jpg', + 'description': ('Watch Press TV’s full interview with Max Igan, a radio talk show host and political ' + 'commentator.\nThe interview, conducted on Press TV’s Face ' + 'to Face program, was aired on October 3, 2015.') + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + # extract video URL from webpage + video_url = self._html_search_regex(r'', webpage, + 'Video URL') + + # build list of available formats + # specified in http://www.presstv.ir/Scripts/playback.js + base_url = 'http://192.99.219.222:82/presstv' + formats = [ + { + 'url': base_url + video_url, + 'format': '1080p mp4', + 'format_id': '1080p' + }, { + 'url': base_url + video_url.replace(".mp4", "_low800.mp4"), + 'format': '720p mp4', + 'format_id': '720p' + }, { + 'url': base_url + video_url.replace(".mp4", "_low400.mp4"), + 'format': '360p mp4', + 'format_id': '360p' + }, { + 'url': base_url + video_url.replace(".mp4", "_low200.mp4"), + 'format': '180p mp4', + 'format_id': '180p' + } + ] + formats.reverse() + + # extract video metadata + title = self._html_search_meta('title', webpage, 'Title', True) + title = title.partition(' - ')[2] + + description = self._html_search_regex(r'
(.*?)
', webpage, + 'Description', flags=re.DOTALL) + + thumbnail = self._html_search_meta('og:image', webpage, 'Thumbnail', True) + + year = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload year', group='y')) + month = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload month', group='m')) + day = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload day', group='d')) + upload_date = '%04d%02d%02d' % (year, month, day) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'description': description + }