From 2a1325fdde5c88fc052710b3c42fcc0d73153901 Mon Sep 17 00:00:00 2001 From: net Date: Sat, 27 Sep 2014 20:11:22 +0300 Subject: [PATCH 1/2] [ynet] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/ynet.py | 47 ++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) create mode 100644 youtube_dl/extractor/ynet.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1f1fc0eb2..944e356ae 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -450,6 +450,7 @@ from .yahoo import ( YahooNewsIE, YahooSearchIE, ) +from .ynet import YnetIE from .youjizz import YouJizzIE from .youku import YoukuIE from .youporn import YouPornIE diff --git a/youtube_dl/extractor/ynet.py b/youtube_dl/extractor/ynet.py new file mode 100644 index 000000000..94d253679 --- /dev/null +++ b/youtube_dl/extractor/ynet.py @@ -0,0 +1,47 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import base64 +import json + +from .common import InfoExtractor +from youtube_dl.utils import compat_urllib_parse_urlparse, compat_urllib_parse + +class YnetIE(InfoExtractor): + _VALID_URL = r'http://.*ynet\.co\.il/.*/0,7340,(?PL(-[0-9]+)+),00\.html' + _TEST = { + 'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html', + 'info_dict': { + 'id': 'L-11659-99244', + 'ext': 'flv', + 'title': 'md5:3dba12d2837ee2ad9652cc64af652b16', + 'thumbnail': 'http://hot.ynet.co.il/PicServer4/2014/09/23/5606015/AMERICAN_COMMUNE1_T.jpg', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + + id = mobj.group('id') + + webpage = self._download_webpage(url, id) + + content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage).decode('utf-8')) + + player_url = re.match('(http.*\.swf)\?' ,content).group(1) + + config = json.loads(re.match('.*config\=(.*)' ,content).group(1)) + + f4m_url = config['clip']['url'] + + title = re.sub(': Video$', '', self._og_search_title(webpage)) + + return { + 'id': id, + 'title': title, + 'formats': self._extract_f4m_formats(f4m_url, id), + 'thumbnail': self._og_search_thumbnail(webpage), + 'player_url': player_url, + } + From c6641823238ac70091520fe9b4b02ec3d41cb1a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 28 Sep 2014 03:26:38 +0700 Subject: [PATCH 2/2] [ynet] Remove unused stuff, simplify and improve --- youtube_dl/extractor/ynet.py | 63 ++++++++++++++++++++---------------- 1 file changed, 35 insertions(+), 28 deletions(-) diff --git a/youtube_dl/extractor/ynet.py b/youtube_dl/extractor/ynet.py index 94d253679..66d53962a 100644 --- a/youtube_dl/extractor/ynet.py +++ b/youtube_dl/extractor/ynet.py @@ -2,46 +2,53 @@ from __future__ import unicode_literals import re -import base64 import json from .common import InfoExtractor -from youtube_dl.utils import compat_urllib_parse_urlparse, compat_urllib_parse +from ..utils import compat_urllib_parse + class YnetIE(InfoExtractor): - _VALID_URL = r'http://.*ynet\.co\.il/.*/0,7340,(?PL(-[0-9]+)+),00\.html' - _TEST = { - 'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html', - 'info_dict': { - 'id': 'L-11659-99244', - 'ext': 'flv', - 'title': 'md5:3dba12d2837ee2ad9652cc64af652b16', - 'thumbnail': 'http://hot.ynet.co.il/PicServer4/2014/09/23/5606015/AMERICAN_COMMUNE1_T.jpg', + _VALID_URL = r'http://.*ynet\.co\.il/.*/0,7340,(?PL(?:-[0-9]+)+),00\.html' + _TESTS = [ + { + 'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html', + 'md5': '002b44ee2f33d50363a1c153bed524cf', + 'info_dict': { + 'id': 'L-11659-99244', + 'ext': 'flv', + 'title': 'איש לא יודע מאיפה באנו', + 'thumbnail': 're:^https?://.*\.jpg', + } + }, { + 'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html', + 'md5': '6455046ae1b48cf7e2b7cae285e53a16', + 'info_dict': { + 'id': 'L-8859-84418', + 'ext': 'flv', + 'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין", + 'thumbnail': 're:^https?://.*\.jpg', + } } - } + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') - id = mobj.group('id') - - webpage = self._download_webpage(url, id) + webpage = self._download_webpage(url, video_id) - content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage).decode('utf-8')) - - player_url = re.match('(http.*\.swf)\?' ,content).group(1) - - config = json.loads(re.match('.*config\=(.*)' ,content).group(1)) - - f4m_url = config['clip']['url'] - - title = re.sub(': Video$', '', self._og_search_title(webpage)) + content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage)) + config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config')) + f4m_url = config['clip']['url'] + title = self._og_search_title(webpage) + m = re.search(r'ynet - HOT -- (["\']+)(?P.+?)\1', title) + if m: + title = m.group('title') return { - 'id': id, + 'id': video_id, 'title': title, - 'formats': self._extract_f4m_formats(f4m_url, id), + 'formats': self._extract_f4m_formats(f4m_url, video_id), 'thumbnail': self._og_search_thumbnail(webpage), - 'player_url': player_url, - } - + } \ No newline at end of file