From 61e2331ad83569b3256e32f415c22cc439c000ed Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 1 Apr 2017 23:47:35 +0100 Subject: [PATCH] [tv5mondeplus] Add new extractor(closes #11386) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/tv5mondeplus.py | 78 ++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+) create mode 100644 youtube_dl/extractor/tv5mondeplus.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d9e8d53ac..46e5e3a1d 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1023,6 +1023,7 @@ ) from .tv3 import TV3IE from .tv4 import TV4IE +from .tv5mondeplus import TV5MondePlusIE from .tva import TVAIE from .tvanouvelles import ( TVANouvellesIE, diff --git a/youtube_dl/extractor/tv5mondeplus.py b/youtube_dl/extractor/tv5mondeplus.py new file mode 100644 index 000000000..8b2d7812a --- /dev/null +++ b/youtube_dl/extractor/tv5mondeplus.py @@ -0,0 +1,78 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + extract_attributes, + get_element_by_class, + int_or_none, + parse_duration, + parse_iso8601, +) + + +class TV5MondePlusIE(InfoExtractor): + IE_DESC = 'TV5MONDE+' + _VALID_URL = r'https?://(?:www\.)?tv5mondeplus\.com/toutes-les-videos/[^/]+/(?P[^/?#]+)' + _TEST = { + 'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants', + 'md5': '12130fc199f020673138a83466542ec6', + 'info_dict': { + 'id': '0a774110-dc60-4037-f769-996439514f1f', + 'ext': 'mp4', + 'title': 'Tdah, mon amour - Enfants', + 'description': 'md5:b65f0cc50e46947e62e5d352e9916cc4', + 'upload_date': '20170401', + 'timestamp': 1491022860, + } + } + _GEO_BYPASS = False + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage: + self.raise_geo_restricted(countries=['FR']) + + series = get_element_by_class('video-detail__title', webpage) + title = episode = get_element_by_class( + 'video-detail__subtitle', webpage) or series + if series and series != title: + title = '%s - %s' % (series, title) + vpl_data = extract_attributes(self._search_regex( + r'(<[^>]+class="video_player_loader"[^>]+>)', + webpage, 'video player loader')) + + video_files = self._parse_json( + vpl_data['data-broadcast'], display_id).get('files', []) + formats = [] + for video_file in video_files: + v_url = video_file.get('url') + if not v_url: + continue + video_format = video_file.get('format') or determine_ext(v_url) + if video_format == 'm3u8': + formats.extend(self._extract_m3u8_formats( + v_url, display_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + else: + formats.append({ + 'url': v_url, + 'format_id': video_format, + }) + self._sort_formats(formats) + + return { + 'id': vpl_data.get('data-guid') or display_id, + 'display_id': display_id, + 'title': title, + 'description': get_element_by_class('video-detail__description', webpage), + 'thumbnail': vpl_data.get('data-image'), + 'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)), + 'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage)), + 'formats': formats, + 'episode': episode, + 'series': series, + }