From dcb00da49cf1edcfc7bf3bc779de3afdea5c3412 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 10 Mar 2014 16:41:04 +0100 Subject: [PATCH] [depositfiles] Remove extractor This site requires a CAPTCHA to download, supports arbitrary files and not only audio/video, and I can't find a single uncopyrighted video with a quick google search. Closes #1255 --- youtube_dl/extractor/__init__.py | 1 - youtube_dl/extractor/depositfiles.py | 60 ---------------------------- 2 files changed, 61 deletions(-) delete mode 100644 youtube_dl/extractor/depositfiles.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d43e6b764..9888c95df 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -53,7 +53,6 @@ from .dailymotion import ( DailymotionUserIE, ) from .daum import DaumIE -from .depositfiles import DepositFilesIE from .dotsub import DotsubIE from .dreisat import DreiSatIE from .defense import DefenseGouvFrIE diff --git a/youtube_dl/extractor/depositfiles.py b/youtube_dl/extractor/depositfiles.py deleted file mode 100644 index 2c9fb5f2e..000000000 --- a/youtube_dl/extractor/depositfiles.py +++ /dev/null @@ -1,60 +0,0 @@ -import re -import os -import socket - -from .common import InfoExtractor -from ..utils import ( - compat_http_client, - compat_str, - compat_urllib_error, - compat_urllib_parse, - compat_urllib_request, - - ExtractorError, -) - - -class DepositFilesIE(InfoExtractor): - """Information extractor for depositfiles.com""" - - _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' - - def _real_extract(self, url): - file_id = url.split('/')[-1] - # Rebuild url in english locale - url = 'http://depositfiles.com/en/files/' + file_id - - # Retrieve file webpage with 'Free download' button pressed - free_download_indication = {'gateway_result' : '1'} - request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication)) - try: - self.report_download_webpage(file_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to retrieve file webpage: %s' % compat_str(err)) - - # Search for the real file URL - mobj = re.search(r'
(Attention.*?)', webpage, re.DOTALL) - if (mobj is not None) and (mobj.group(1) is not None): - restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() - raise ExtractorError(u'%s' % restriction_message) - else: - raise ExtractorError(u'Unable to extract download URL from: %s' % url) - - file_url = mobj.group(1) - file_extension = os.path.splitext(file_url)[1][1:] - - # Search for file title - file_title = self._search_regex(r'', webpage, u'title') - - return [{ - 'id': file_id.decode('utf-8'), - 'url': file_url.decode('utf-8'), - 'uploader': None, - 'upload_date': None, - 'title': file_title, - 'ext': file_extension.decode('utf-8'), - }] -- 2.30.2