mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-09-06 02:49:35 +02:00
[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
This commit is contained in:
parent
ae7ed92057
commit
dcb00da49c
@ -53,7 +53,6 @@
|
||||
DailymotionUserIE,
|
||||
)
|
||||
from .daum import DaumIE
|
||||
from .depositfiles import DepositFilesIE
|
||||
from .dotsub import DotsubIE
|
||||
from .dreisat import DreiSatIE
|
||||
from .defense import DefenseGouvFrIE
|
||||
|
@ -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'<form action="(http://fileshare.+?)"', webpage)
|
||||
if (mobj is None) or (mobj.group(1) is None):
|
||||
# Try to figure out reason of the error.
|
||||
mobj = re.search(r'<strong>(Attention.*?)</strong>', 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'<b title="(.*?)">', 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'),
|
||||
}]
|
Loading…
Reference in New Issue
Block a user