Das deutsche Python-Forum

Code: Alles auswählen

# -*- coding: utf-8 -*-
from urllib.parse import urlencode
from urllib.request import build_opener, HTTPCookieProcessor
from http.cookiejar import CookieJar
from time import sleep
from shutil import copyfileobj
import os
import re

class CookieCon_ret(object):
	def __init__(self, encoding='utf-8', userAgent=None):
		self._encoding = encoding
		self._cookiejar = CookieJar()
		self._opener = build_opener(HTTPCookieProcessor(self._cookiejar))
		if not userAgent is None:
			self._opener.addheaders = [('User-agent', userAgent)]

	def urlretrieve(self, url, folder, optname = None):
		"""Used for files"""
		with self._opener.open(url) as sock:
			foo = sock.info()['Content-Disposition']
			if optname is None:
				#yeah, this is not correct but regex is a fucking pain in the ass right now
				filename = foo[22:-1]
			else:
				filename = optname
			filepath = os.path.join(folder, filename)
			if not os.path.exists(filepath):
				with open(filepath, "wb") as file:
					copyfileobj(sock, file)

Code: Alles auswählen

def urlretrieve(self, url, folder, optname = None):
	"""Used for files"""
	with self._opener.open(url) as sock:
		foo = sock.info()['Content-Disposition']
		if optname is None:
			#yeah, this is not correct but regex is a fucking pain in the ass right now
			filename = foo[22:-1]
		else:
			filename = optname
		filepath = os.path.join(folder, filename)
		if not os.path.exists(filepath):
			file_options = "wb"
			currentSize = 0
		else:
			file_option = "ab"
			currentSize = os.path.getsize(filepath)
		maxSize = int(sock.headers['Content-Length'])
	if currentSize < maxSize:
		if currentSize:
			self._opener.add_header("Range","bytes=%s-" % (currentSize))
		with self._opener.open(url) as sock, open(filepath, file_options) as file:
			copyfileobj(sock, file)
		if currentSize:
			self._opener.remove_header("Range","bytes=%s-" % (currentSize))

Code: Alles auswählen

    def get_filename_from_url(self, url):
        with self._opener.open(url) as sock:
            return sock.info()['Content-Disposition'].split(':',1)[-1].strip()

    def retrieve_url(self, url, folder, optname=None):
        """Used for urls"""
        filename = optname if optname else self.get_filename_from_url(url)
        filepath = os.path.join(folder, filename)
        if os.path.exists(filepath):
            self._opener.add_header("Range","bytes=%d-" % os.path.getsize(filepath))
        with self._opener.open(url) as sock, open(filepath, "ab") as file:
            copyfileobj(sock, file)
        self._opener.headers.pop('Range', None)