爬虫-ip代理
2018-03-21 14:00
288 查看
from urllib.request import urlopen,Request,ProxyHandler,build_opener,install_opener url = 'http://ip.chinaz.com/getip.aspx' #局部代理 # handler = ProxyHandler({'http':'115.223.215.51:9000'}) # opener = build_opener(handler) # html = opener.open(url).read().decode() # print(html) #全局代理 handler = ProxyHandler({'http':'115.223.215.51:9000'}) opener = build_opener(handler) install_opener(opener) #设置好了全局IP代理 html = urlopen(url).read().decode() print(html)
from urllib.request import urlopen,Request,urlparse,ProxyHandler,build_opener,install_opener from urllib.error import URLError,HTTPError pcUserAgent = { "safari 5.1 – MAC":"User-Agent:Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50", "safari 5.1 – Windows":"User-Agent:Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50", "IE 9.0":"User-Agent:Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0);", "IE 8.0":"User-Agent:Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)", "IE 7.0":"User-Agent:Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)", "IE 6.0":"User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)", "Firefox 4.0.1 – MAC":"User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1", "Firefox 4.0.1 – Windows":"User-Agent:Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1", "Opera 11.11 – MAC":"User-Agent:Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11", "Opera 11.11 – Windows":"User-Agent:Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11", "Chrome 17.0 – MAC":"User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11", "Maxthon":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)", "Tencent TT":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)", "The World 2.x":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)", "The World 3.x":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)", "sogou 1.x":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)", "360":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)", "Avant":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)", "Green Browser":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)" } mobileUserAgent = { "iOS 4.33 – iPhone":"User-Agent:Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5", "iOS 4.33 – iPod Touch":"User-Agent:Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5", "iOS 4.33 – iPad":"User-Agent:Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5", "Android N1":"User-Agent: Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1", "Android QQ":"User-Agent: MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1", "Android Opera ":"User-Agent: Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10", "Android Pad Moto Xoom":"User-Agent: Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13", "BlackBerry":"User-Agent: Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+", "WebOS HP Touchpad":"User-Agent: Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0", "Nokia N97":"User-Agent: Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124", "Windows Phone Mango":"User-Agent: Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)", "UC":"User-Agent: UCWEB7.0.2.37/28/999", "UC standard":"User-Agent: NOKIA5700/ UCWEB7.0.2.37/28/999", "UCOpenwave":"User-Agent: Openwave/ UCWEB7.0.2.37/28/999", "UC Opera":"User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999" } #url = 'http://sou.zhaopin.com/jobs/searchresult.ashx?jl=%E5%A4%AA%E5%8E%9F&kw=python&p=1&isadv=0' #url = 'http://httpstat.us/500' #url = 'http://avashkdjhjzxhcjzkxc.com' url = 'https://www.baidu.com/' def download(url, num_retries=3, user_agent='test',proxy=None): print('[+]Download... %s'% url) if proxy: handler = ProxyHandler({urlparse(url).scheme:proxy}) opener = build_opener(handler) install_opener(opener) try: headers = {'User-Agent':user_agent} req = Request(url, headers=headers) re = urlopen(req) code_ = re.info()[re.info().keys()[1]].split('=')[-1] #Content-Type html = re.read().decode('utf-8') except HTTPError as e: b98c html = None if num_retries > 0: print('[E]HttpError Try Download %d times' % (3 - num_retries)) if hasattr(e,'code') and 500<= e.code < 600: html = download(url,num_retries-1) else: print('[E]Failed!!') except URLError as e: html = None print('[E]Unloacted URL! ',url) return html # pc_ug = pcUserAgent['360'] # mb_ug = mobileUserAgent["iOS 4.33 – iPhone"] # pc_html = download(url,user_agent=pc_ug) # mb_html = download(url,user_agent=mb_ug) # pc_file = open('pc.html','w',encoding='utf-8') # mb_file = open('mb.html','w',encoding='utf-8') # pc_file.write(pc_html) # mb_file.write(mb_html) # pc_file.close() # mb_file.close()
相关文章推荐
- python获取ip代理列表爬虫
- 可能是一份没什么用的爬虫代理IP指南 - 程序猿的自我修养 - 博客园
- Python爬虫实战——代理IP全部抓取
- Python 爬虫入门(二)—— IP代理使用
- Python:爬虫使用代理防封IP:HTTP Error 403: Forbidden
- 使用python为爬虫获取免费代理ip
- Python爬虫抓取代理IP并检验可用性
- 网络爬虫爬取全国省市区(动态ip代理的获取,实现对ip限制的突破)
- Java爬虫爬取代理ip
- python爬虫入门(二)——爬取代理IP
- Jsoup使用代理ip爬虫
- Java爬虫——代理IP
- 第三百四十八节,Python分布式爬虫打造搜索引擎Scrapy精讲—通过自定义中间件全局随机更换代理IP
- 反反爬虫 IP代理
- Python3 爬虫使用User Agent和代理IP隐藏身份
- Scrapy爬虫:代理IP配置
- Python 爬虫IP代理
- 关于网络爬虫及ip代理服务的理解
- Python 爬虫入门(二)—— IP代理使用 - 不剃头的一休哥 - 博客园
- 通过Python爬虫代理IP快速增加博客阅读量