From 426ff04282ac04e258323066b385e434d7329cc0 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 21:06:20 +0200 Subject: [PATCH] Move DepositFiles into its own IE --- youtube_dl/InfoExtractors.py | 45 +-------------------- youtube_dl/extractor/depositfiles.py | 60 ++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+), 44 deletions(-) create mode 100644 youtube_dl/extractor/depositfiles.py diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 77b9f3581e..e650e7bcf2 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -23,6 +23,7 @@ from .extractor.bliptv import BlipTVIE, BlipTVUserIE from .extractor.comedycentral import ComedyCentralIE from .extractor.dailymotion import DailymotionIE +from .extractor.depositfiles import DepositFilesIE from .extractor.facebook import FacebookIE from .extractor.gametrailers import GametrailersIE from .extractor.generic import GenericIE @@ -56,50 +57,6 @@ -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'), - }] diff --git a/youtube_dl/extractor/depositfiles.py b/youtube_dl/extractor/depositfiles.py new file mode 100644 index 0000000000..d43348955f --- /dev/null +++ b/youtube_dl/extractor/depositfiles.py @@ -0,0 +1,60 @@ +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'), + }]