From 256a746d21634eccad07a1e6dcafedcdf8b6181b Mon Sep 17 00:00:00 2001 From: luboss Date: Fri, 2 Jun 2017 22:44:39 +0200 Subject: [PATCH] [joj] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/joj.py | 56 ++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100755 youtube_dl/extractor/joj.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 4524fa687..9ee080895 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -470,6 +470,7 @@ from .jamendo import ( ) from .jeuxvideo import JeuxVideoIE from .jove import JoveIE +from .joj import JojIE from .jwplatform import JWPlatformIE from .jpopsukitv import JpopsukiIE from .kaltura import KalturaIE diff --git a/youtube_dl/extractor/joj.py b/youtube_dl/extractor/joj.py new file mode 100755 index 000000000..2ebfec902 --- /dev/null +++ b/youtube_dl/extractor/joj.py @@ -0,0 +1,56 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +import re + + +class JojIE(InfoExtractor): + _VALID_URL = r'https?://[a-z0-9]+\.joj\.sk/([^/]+/)*(?P(?P[0-9]{4}(-[0-9]{2}){2}).*)' # noqa + _TESTS = [{ + 'url': 'https://www.joj.sk/nove-byvanie/archiv/2017-05-28-nove-byvanie', # noqa + 'info_dict': { + 'id': 'a388ec4c-6019-4a4a-9312-b1bee194e932', + 'ext': 'mp4', + 'title': 'Nové Bývanie', + 'release_date': '20170528' + } + }, { + 'url': 'http://nasi.joj.sk/epizody/2016-09-06-stari-rodicia', + 'info_dict': { + 'id': 'f18b2c5f-9ea8-4941-a164-a814c53306ad', + 'ext': 'mp4', + 'title': 'Starí Rodičia', + 'release_date': '20160906' + } + }] + + media_src_url = 'http://n16.joj.sk/storage/' + xml_source_url = 'https://media.joj.sk/services/Video.php?clip=' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + release_date = mobj.group('release_date').replace('-', '') + webpage = self._download_webpage(url, 'id') + video_id = self._html_search_regex( + r'https?://([a-z0-9]+\.)joj\.sk/embed/(?P[a-f0-9\-]+)', + webpage, 'id', group='video_id') + xml_playlist_url = self.xml_source_url + video_id + xml_playlist_et = self._download_xml(xml_playlist_url, 'XML playlist') + formats = [] + for file_el in xml_playlist_et.findall('files/file'): + try: + height = int(file_el.attrib['id'].replace('p', '')) + except ValueError: + height = 0 + formats.append({'height': height, + 'url': self.media_src_url + file_el.attrib['path'].replace( # noqa + 'dat/', '', 1)}) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage).title(), + 'formats': formats, + 'release_date': release_date + }