From 678f58de4bf8c07116e4ea2255770ab0ba665c14 Mon Sep 17 00:00:00 2001 From: Naglis Jonaitis Date: Sat, 12 Jul 2014 00:42:42 +0300 Subject: [PATCH] [firedrive] Add new extractor. Addresses #3095 --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/firedrive.py | 81 +++++++++++++++++++++++++++++++ 2 files changed, 82 insertions(+) create mode 100644 youtube_dl/extractor/firedrive.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 15d2f0e2a..c215811c3 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -83,6 +83,7 @@ from .facebook import FacebookIE from .faz import FazIE from .fc2 import FC2IE +from .firedrive import FiredriveIE from .firstpost import FirstpostIE from .firsttv import FirstTVIE from .fivemin import FiveMinIE diff --git a/youtube_dl/extractor/firedrive.py b/youtube_dl/extractor/firedrive.py new file mode 100644 index 000000000..1d83048e8 --- /dev/null +++ b/youtube_dl/extractor/firedrive.py @@ -0,0 +1,81 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_parse, + compat_urllib_request, + determine_ext, +) + + +class FiredriveIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?firedrive\.com/' + \ + '(?:file|embed)/(?P[0-9a-zA-Z]+)' + _FILE_DELETED_REGEX = r'
' + + _TESTS = [{ + 'url': 'https://www.firedrive.com/file/FEB892FA160EBD01', + 'md5': 'd5d4252f80ebeab4dc2d5ceaed1b7970', + 'info_dict': { + 'id': 'FEB892FA160EBD01', + 'ext': 'flv', + 'title': 'bbb_theora_486kbit.flv', + 'thumbnail': 're:http://.*\.jpg', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://firedrive.com/file/%s' % video_id + + webpage = self._download_webpage(url, video_id) + + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: + raise ExtractorError(u'Video %s does not exist' % video_id, + expected=True) + + fields = dict(re.findall(r'''(?x)(.+)
', + webpage, 'title') + thumbnail = self._search_regex(r'image:\s?"(//[^\"]+)', webpage, + 'thumbnail', fatal=False, default="") + url = self._search_regex(r'file:\s?\'(http[^\']+)\',', + webpage, 'file url') + ext = self._search_regex(r'type:\s?\'([^\']+)\',', + webpage, 'extension', fatal=False) + + formats = [{ + 'format_id': 'sd', + 'url': url, + 'ext': ext or determine_ext(url), + 'quality': 1, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': "http:" + thumbnail, + 'formats': formats, + }