Python实现爬虫设置代理IP和伪装成浏览器的方法分享
1.python爬虫浏览器伪装
123456789101112 | #导入urllib.request模块 import urllib.request #设置请求头 headers=("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0") #创建一个opener opener=urllib.request.build_opener() #将headers添加到opener中 opener.addheaders=[headers] #将opener安装为全局 urllib.request.install_opener(opener) #用urlopen打开网页 data=urllib.request.urlopen(url).read().decode('utf-8','ignore') |
2.设置代理
12345678910 | #定义代理ip proxy_addr="122.241.72.191:808" #设置代理 proxy=urllib.request.ProxyHandle({'http':proxy_addr}) #创建一个opener opener=urllib.request.build_opener(proxy,urllib.request.HTTPHandle) #将opener安装为全局 urllib.request.install_opener(opener) #用urlopen打开网页 data=urllib.request.urlopen(url).read().decode('utf-8','ignore') |
3.同时设置用代理和模拟浏览器访问
1234567891011121314 | #定义代理ip proxy_addr="122.241.72.191:808" #创建一个请求 req=urllib.request.Request(url) #添加headers req.add_header("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) #设置代理 proxy=urllib.request.ProxyHandle("http":proxy_addr) #创建一个opener opener=urllib.request.build_opener(proxy,urllib.request.HTTPHandle) #将opener安装为全局 urllib.request.install_opener(opener) #用urlopen打开网页 data=urllib.request.urlopen(req).read().decode('utf-8','ignore') |
4.在请求头中添加多个信息
1234567 | import urllib.request page_headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0", "Host":"www.baidu.com", "Cookie":"xxxxxxxx" } req=urllib.request.Request(url,headers=page_headers) data=urllib.request.urlopen(req).read().decode('utf-8','ignore') |
5.添加post请求参数
1234567891011121314151617181920212223 | import urllib.request import urllib.parse #设置post参数 page_data=urllib.parse.urlencode([ ('pn',page_num), ('kd',keywords) ]) #设置headers page_headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0', 'Connection':'keep-alive', 'Host':'www.lagou.com', 'Origin':'https://www.lagou.com', 'Cookie':'JSESSIONID=ABAAABAABEEAAJA8F28C00A88DC4D771796BB5C6FFA2DDA; user_trace_token=20170715131136-d58c1f22f6434e9992fc0b35819a572b', 'Accept':'application/json, text/javascript, */*; q=0.01', 'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8', 'Referer':'https://www.lagou.com/jobs/list_%E6%95%B0%E6%8D%AE%E6%8C%96%E6%8E%98?labelWords=&fromSearch=true&suginput=', 'X-Anit-Forge-Token':'None', 'X-Requested-With':'XMLHttpRequest' } #打开网页 req=urllib.request.Request(url,headers=page_headers) data=urllib.request.urlopen(req,data=page_data.encode('utf-8')).read().decode('utf-8') |
6.利用phantomjs模拟浏览器请求
123456789 | #1.下载phantomjs安装到本地,并设置环境变量 from selenium import webdriver bs=webdriver.PhantomJS() #打开url bs.get(url) #获取网页源码 url_data=bs.page_source #将浏览到的网页保存为图片 bs.get_screenshot_as_file(filename) |
7.phantomjs设置user-agent和cookie
123456789101112131415161718 | from selenium import webdriver from selenium.webdriver.common.desired_capabilities import DesiredCapabilities dcap = dict(DesiredCapabilities.PHANTOMJS) dcap["phantomjs.page.settings.userAgent"] = ("Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0") bs = webdriver.PhantomJS(desired_capabilities=dcap) bs.get(url) #删除cookie bs.delete_all_cookies() #设置cookie #cookie格式:在浏览器cookie中查看,一个cookie需要包含以下参数,domain、name、value、path cookie={ 'domain':'.www.baidu.com', #注意前面有. 'name':'xxxx', 'value':'xxxx', 'path':'xxxx' } #向phantomjs中添加cookie bs.add_cookie(cookie) |
8.利用web_driver工具
123456 | #1.下载web_driver工具(如chromdriver.exe)及对应的浏览器 #2.将chromdriver.exe放到某个目录,如c:\chromdriver.exe from selenium import webdriver driver=webdriver.Chrome(executable_path="C:\chromdriver.exe") #打开url driver.get(url) |