From 734d461ca04a9f271dd463aa75d44ac82377057e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 16 Jun 2018 21:14:36 +0700 Subject: [PATCH] [expressen] Add extractor --- youtube_dl/extractor/expressen.py | 77 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 78 insertions(+) create mode 100644 youtube_dl/extractor/expressen.py diff --git a/youtube_dl/extractor/expressen.py b/youtube_dl/extractor/expressen.py new file mode 100644 index 000000000..f61178012 --- /dev/null +++ b/youtube_dl/extractor/expressen.py @@ -0,0 +1,77 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + int_or_none, + unescapeHTML, + unified_timestamp, +) + + +class ExpressenIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?expressen\.se/tv/(?:[^/]+/)*(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/', + 'md5': '2fbbe3ca14392a6b1b36941858d33a45', + 'info_dict': { + 'id': '8690962', + 'ext': 'mp4', + 'title': 'Ledarsnack: Om arbetslösheten bland kvinnor i speciellt utsatta områden', + 'description': 'md5:f38c81ff69f3de4d269bbda012fcbbba', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 788, + 'timestamp': 1526639109, + 'upload_date': '20180518', + }, + }, { + 'url': 'https://www.expressen.se/tv/kultur/kulturdebatt-med-expressens-karin-olsson/', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + def extract_data(name): + return self._parse_json( + self._search_regex( + r'data-%s=(["\'])(?P(?:(?!\1).)+)\1' % name, + webpage, 'info', group='value'), + display_id, transform_source=unescapeHTML) + + info = extract_data('video-tracking-info') + video_id = info['videoId'] + + data = extract_data('article-data') + stream = data['stream'] + + if determine_ext(stream) == 'm3u8': + formats = self._extract_m3u8_formats( + stream, display_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + else: + formats = [{ + 'url': stream, + }] + self._sort_formats(formats) + + title = info.get('titleRaw') or data['title'] + description = info.get('descriptionRaw') + thumbnail = info.get('socialMediaImage') or data.get('image') + duration = int_or_none(info.get('videoTotalSecondsDuration') or + data.get('totalSecondsDuration')) + timestamp = unified_timestamp(info.get('publishDate')) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d4583b8e4..c3e6daa24 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -335,6 +335,7 @@ from .esri import EsriVideoIE from .europa import EuropaIE from .everyonesmixtape import EveryonesMixtapeIE from .expotv import ExpoTVIE +from .expressen import ExpressenIE from .extremetube import ExtremeTubeIE from .eyedotv import EyedoTVIE from .facebook import (