From 423817c468d67e592145f1390b9c160455a9bcca Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 24 Aug 2014 06:41:55 +0200 Subject: [PATCH] [expotv] Add new extractor (Fixes #3552) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/expotv.py | 73 ++++++++++++++++++++++++++++++++ youtube_dl/utils.py | 1 + 3 files changed, 75 insertions(+) create mode 100644 youtube_dl/extractor/expotv.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9dccbb8ed..0203d9d63 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -88,6 +88,7 @@ from .engadget import EngadgetIE from .escapist import EscapistIE from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE +from .expotv import ExpoTVIE from .extremetube import ExtremeTubeIE from .facebook import FacebookIE from .faz import FazIE diff --git a/youtube_dl/extractor/expotv.py b/youtube_dl/extractor/expotv.py new file mode 100644 index 000000000..a38b773e8 --- /dev/null +++ b/youtube_dl/extractor/expotv.py @@ -0,0 +1,73 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + unified_strdate, +) + + +class ExpoTVIE(InfoExtractor): + _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P[0-9]+)($|[?#])' + _TEST = { + 'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561', + 'md5': '2985e6d7a392b2f7a05e0ca350fe41d0', + 'info_dict': { + 'id': '17561', + 'ext': 'mp4', + 'upload_date': '20060212', + 'title': 'My Favorite Online Scrapbook Store', + 'view_count': int, + 'description': 'You\'ll find most everything you need at this virtual store front.', + 'uploader': 'Anna T.', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_key = self._search_regex( + r'Plays: ([0-9]+)', webpage, 'view counts')) + uploader = self._search_regex( + r'
\s*([^Reviewed on ([0-9/.]+)', webpage, 'upload date', + fatal=False)) + + return { + 'id': video_id, + 'formats': formats, + 'title': title, + 'description': description, + 'view_count': view_count, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'upload_date': upload_date, + } diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index ac8a78adf..8095400d0 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -855,6 +855,7 @@ def unified_strdate(date_str): '%Y/%m/%d', '%d.%m.%Y', '%d/%m/%Y', + '%d/%m/%y', '%Y/%m/%d %H:%M:%S', '%Y-%m-%d %H:%M:%S', '%d.%m.%Y %H:%M',