From dbe80ca7adabb23f91fbd1aaaf1151af3942eb26 Mon Sep 17 00:00:00 2001 From: "Sergey M." Date: Mon, 3 Feb 2014 01:20:03 +0700 Subject: [PATCH] [tinypic] Add support for tinypic.com videos (Closes #2210) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/tinypic.py | 50 ++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) create mode 100644 youtube_dl/extractor/tinypic.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9b346ac68..073f3a0d1 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -200,6 +200,7 @@ from .ted import TEDIE from .tf1 import TF1IE from .theplatform import ThePlatformIE from .thisav import ThisAVIE +from .tinypic import TinyPicIE from .toutv import TouTvIE from .traileraddict import TrailerAddictIE from .trilulilu import TriluliluIE diff --git a/youtube_dl/extractor/tinypic.py b/youtube_dl/extractor/tinypic.py new file mode 100644 index 000000000..2246d27b2 --- /dev/null +++ b/youtube_dl/extractor/tinypic.py @@ -0,0 +1,50 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from youtube_dl.utils import ExtractorError + + +class TinyPicIE(InfoExtractor): + IE_NAME = 'tinypic' + IE_DESC = 'tinypic.com videos' + _VALID_URL = r'http://tinypic\.com/player\.php\?v=(?P[^&]+)&s=\d+' + + _TEST = { + 'url': 'http://tinypic.com/player.php?v=6xw7tc%3E&s=5#.UtqZmbRFCM8', + 'md5': '609b74432465364e72727ebc6203f044', + 'info_dict': { + 'id': '6xw7tc', + 'ext': 'flv', + 'title': 'shadow phenomenon weird', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id, 'Downloading page') + + mobj = re.search(r'(?m)fo\.addVariable\("file",\s"(?P[\da-z]+)"\);\n' + '\s+fo\.addVariable\("s",\s"(?P\d+)"\);', webpage) + if mobj is None: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + + file_id = mobj.group('fileid') + server_id = mobj.group('serverid') + + KEYWORDS_SUFFIX = ', Video, images, photos, videos, myspace, ebay, video hosting, photo hosting' + keywords = self._html_search_meta('keywords', webpage, 'title') + title = keywords[:-len(KEYWORDS_SUFFIX)] if keywords.endswith(KEYWORDS_SUFFIX) else '' + + video_url = 'http://v%s.tinypic.com/%s.flv' % (server_id, file_id) + thumbnail = 'http://v%s.tinypic.com/%s_th.jpg' % (server_id, file_id) + + return { + 'id': file_id, + 'url': video_url, + 'thumbnail': thumbnail, + 'title': title + } \ No newline at end of file