#!/usr/bin/python
# -*- coding: utf-8 -*-
import random
import requests
import urllib.request
# import urllib3
# 代理服务器
proxyServer = ""
# 代理隧道验证信息
proxies = {'http': 'http://127.0.0.1',
'https': 'http://127.0.0.1'}
# res = requests.get(url, proxies=config.proxy_conf, timeout=20)
class Download(object):
def __init__(self):
self.user_agent = ['Mozilla/5.0 (Windows NT 10.0; WOW64)', 'Mozilla/5.0 (Windows NT 6.3; WOW64)',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:54.0) Gecko/20100101 Firefox/54.0',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; rv:11.0) like Gecko)',
'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12',
'Opera/9.27 (Windows NT 5.2; U; zh-cn)',
'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0',
'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080219 Firefox/2.0.0.12 Navigator/9.0.0.6',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Win64; x64; Trident/4.0)',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Maxthon/4.0.6.2000 Chrome/26.0.1410.43 Safari/537.1 ',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E; QQBrowser/7.3.9825.400)',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0 ',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.92 Safari/537.1 LBBROWSER',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; BIDUBrowser 2.x)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/3.0 Safari/536.11']
def downlaod_get(self, url, proxy=False):
# 使用代理
# proxy_support = urllib.request.ProxyHandler({'https': '127.0.0.1:1080'})
proxy_support = urllib.request.ProxyHandler(proxies)
opener = urllib.request.build_opener(proxy_support)
headers = {'User-Agent': random.choice(self.user_agent)}
req = urllib.request.Request(url, headers=headers)
if proxy:
response = opener.open(req)
else:
response = urllib.request.urlopen(req)
result = response.read()
response.close()
return result
def get_file(self, url):
headers = {'User-Agent': random.choice(self.user_agent)}
response = requests.get(url, headers=headers, proxies=proxies)
return response
if __name__ == '__main__':
D = Download()
# url = "http://www.zsepb.gov.cn/xxgk/bsgk/hjcf/zjcf/201808/P020180821577953104336.doc"
url = 'http://hbj.cbs.gov.cn/zwpt/hjcf/201808/P020180813388890888648.pdf'
# urllib.request.urlretrieve(url)
# print(D.get_file(url).content)
print(D.downlaod_get(url))
requests 有时下载文件出现乱码,使用标准库,原生的解码方式会有意想不到的效果
最后编辑于 :
©著作权归作者所有,转载或内容合作请联系作者
- 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
- 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
- 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...
推荐阅读更多精彩内容
- 【蝴蝶效应】 蝴蝶效应:上个世纪70年代,美国一个名叫洛伦兹的气象学家在解释空气系统理论时说,亚马逊雨林一只蝴蝶...