From: remitamine Date: Mon, 7 Sep 2015 15:39:01 +0000 (+0100) Subject: [canal13cl] fix info extraction X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=8b55cadc83f198e0fa6bac7158f9b05826f39257;p=youtube-dl [canal13cl] fix info extraction --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5d2ea39d0..661b53e63 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -67,7 +67,6 @@ from .camdemy import ( CamdemyIE, CamdemyFolderIE ) -from .canal13cl import Canal13clIE from .canalplus import CanalplusIE from .canalc2 import Canalc2IE from .cbs import CBSIE @@ -612,6 +611,7 @@ from .teachingchannel import TeachingChannelIE from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE +from .tele13 import Tele13IE from .telebruxelles import TeleBruxellesIE from .telecinco import TelecincoIE from .telegraaf import TelegraafIE diff --git a/youtube_dl/extractor/canal13cl.py b/youtube_dl/extractor/canal13cl.py deleted file mode 100644 index 93241fefe..000000000 --- a/youtube_dl/extractor/canal13cl.py +++ /dev/null @@ -1,48 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor - - -class Canal13clIE(InfoExtractor): - _VALID_URL = r'^http://(?:www\.)?13\.cl/(?:[^/?#]+/)*(?P[^/?#]+)' - _TEST = { - 'url': 'http://www.13.cl/t13/nacional/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', - 'md5': '4cb1fa38adcad8fea88487a078831755', - 'info_dict': { - 'id': '1403022125', - 'display_id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', - 'ext': 'mp4', - 'title': 'El "círculo de hierro" de Michelle Bachelet en su regreso a La Moneda', - 'description': '(Foto: Agencia Uno) En nueve días más, Michelle Bachelet va a asumir por segunda vez como presidenta de la República. Entre aquellos que la acompañarán hay caras que se repiten y otras que se consolidan en su entorno de colaboradores más cercanos.', - } - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('id') - - webpage = self._download_webpage(url, display_id) - - title = self._html_search_meta( - 'twitter:title', webpage, 'title', fatal=True) - description = self._html_search_meta( - 'twitter:description', webpage, 'description') - url = self._html_search_regex( - r'articuloVideo = \"(.*?)\"', webpage, 'url') - real_id = self._search_regex( - r'[^0-9]([0-9]{7,})[^0-9]', url, 'id', default=display_id) - thumbnail = self._html_search_regex( - r'articuloImagen = \"(.*?)\"', webpage, 'thumbnail') - - return { - 'id': real_id, - 'display_id': display_id, - 'url': url, - 'title': title, - 'description': description, - 'ext': 'mp4', - 'thumbnail': thumbnail, - } diff --git a/youtube_dl/extractor/tele13.py b/youtube_dl/extractor/tele13.py new file mode 100644 index 000000000..5d89e757f --- /dev/null +++ b/youtube_dl/extractor/tele13.py @@ -0,0 +1,77 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import js_to_json + + +class Tele13IE(InfoExtractor): + _VALID_URL = r'^http://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P[\w-]+)' + _TESTS = [ + { + 'url': 'http://www.t13.cl/videos/actualidad/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', + 'md5': '4cb1fa38adcad8fea88487a078831755', + 'info_dict': { + 'id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', + 'ext': 'mp4', + 'title': 'El c\u00edrculo de hierro de Michelle Bachelet en su regreso a La Moneda', + } + }, + { + 'url': 'http://www.t13.cl/videos/mundo/tendencias/video-captan-misteriosa-bola-fuego-cielos-bangkok', + 'md5': '65d1ae54812c96f4b345dd21d3bb1adc', + 'info_dict': { + 'id': 'rOoKv2OMpOw', + 'ext': 'mp4', + 'title': 'Shooting star seen on 7-Sep-2015', + 'description': 'md5:a1cd2e74f6ee6851552c9cf5851d6b06', + 'uploader': 'Porjai Jaturongkhakun', + 'upload_date': '20150906', + 'uploader_id': 'UCnLY_3ezwNcDSC_Wc6suZxw', + }, + 'add_ie': ['Youtube'], + } + ] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + setup_js = self._parse_json( + js_to_json( + self._search_regex( + r"jwplayer\('player-vivo'\).setup\((\{.*?\})\)", + webpage, + 'setup code', + flags=re.DOTALL + ).replace('\n//', '') + ), + display_id + ) + title = setup_js['title'] + thumbnail = setup_js.get('image') or setup_js['playlist'][0].get('image') + description = self._html_search_meta( + 'description', webpage, 'description') + + formats = [] + for f in setup_js['playlist'][0]['sources']: + format_url = f['file'] + if format_url != '': + if '.m3u8' in format_url: + formats.extend(self._extract_m3u8_formats(format_url, display_id)) + else: + if 'youtube.com' in format_url: + return self.url_result(format_url, 'Youtube') + else: + formats.append({'url': format_url, 'format_id': f.get('label')}) + + return { + 'id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + }