From 0138968a6a5d18e5aca23b52819cd10015997831 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 31 Jul 2014 20:26:52 +0700 Subject: [PATCH] [vidme] Add extractor (Closes #3404) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/vidme.py | 68 ++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) create mode 100644 youtube_dl/extractor/vidme.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5ab89a1bf5..6a9e937afa 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -347,6 +347,7 @@ from .videofyme import VideofyMeIE from .videopremium import VideoPremiumIE from .videott import VideoTtIE from .videoweed import VideoWeedIE +from .vidme import VidmeIE from .vimeo import ( VimeoIE, VimeoChannelIE, diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py new file mode 100644 index 0000000000..5c89824c16 --- /dev/null +++ b/youtube_dl/extractor/vidme.py @@ -0,0 +1,68 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + float_or_none, + str_to_int, +) + + +class VidmeIE(InfoExtractor): + _VALID_URL = r'https?://vid\.me/(?:e/)?(?P[\da-zA-Z]+)' + _TEST = { + 'url': 'https://vid.me/QNB', + 'md5': 'f42d05e7149aeaec5c037b17e5d3dc82', + 'info_dict': { + 'id': 'QNB', + 'ext': 'mp4', + 'title': 'Fishing for piranha - the easy way', + 'description': 'source: https://www.facebook.com/photo.php?v=312276045600871', + 'duration': 119.92, + 'timestamp': 1406313244, + 'upload_date': '20140725', + '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) + + video_url = self._html_search_regex(r'\s*([\d,\.]+)\s*plays?', webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'class="score js-video-vote-score"[^>]+data-score="([\d,\.\s]+)">', + webpage, 'like count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'class="js-comment-count"[^>]+data-count="([\d,\.\s]+)">', + webpage, 'comment count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'width': width, + 'height': height, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'comment_count': comment_count, + }