python3代理ip_Python3.x：代理ip刷评分

你的名字 2023-01-09 12:59 155阅读 0赞

\#python3\#功能：对https://best.zhaopin.com/中的某企业刷评分

importreimportrandomimportsysimporttimeimportdatetimeimportthreadingfrom random importchoiceimportrequestsimportbs4\#设置user-agent列表，每次请求时，可在此列表中随机挑选一个user-agnet

user\_agent =\["Mozilla/5.0 (X11; Ubuntu; Linux x86\_64; rv:17.0; Baiduspider-ads) Gecko/17.0 Firefox/17.0","Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9b4) Gecko/2008030317 Firefox/3.0b4","Mozilla/5.0 (Windows; U; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 2.0.50727; BIDUBrowser 7.6)","Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko","Mozilla/5.0 (Windows NT 6.3; WOW64; rv:46.0) Gecko/20100101 Firefox/46.0","Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.99 Safari/537.36","Mozilla/5.0 (Windows NT 6.3; Win64; x64; Trident/7.0; Touch; LCJB; rv:11.0) like Gecko",

\]\#国内高匿代理IP，返回某页面的所有ip

def get\_ip\_list(page=1):\#获取代理IP(取当前页的ip列表，每页100条ip)

url = "http://www.xicidaili.com/nn/"+page

headers= \{ "Accept":"text/html,application/xhtml+xml,application/xml;","Accept-Encoding":"gzip, deflate, sdch","Accept-Language":"zh-CN,zh;q=0.8,en;q=0.6","Referer":"http://www.xicidaili.com","User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36"\}

r= requests.get(url,headers=headers)

soup= bs4.BeautifulSoup(r.text, 'html.parser')

data= soup.table.find\_all("td")\#匹配规则需要用浏览器的开发者工具进行查看

\#匹配IP：

61.135.217.7

ip\_compile= re.compile(r'

(\\d+\\.\\d+\\.\\d+\\.\\d+)')\#匹配端口：80

port\_compile = re.compile(r'

(\\d+)')\#获取所有IP，返回的是数组\[\]

ip =re.findall(ip\_compile,str(data))\#获取所有端口：返回的是数组\[\]

port =re.findall(port\_compile,str(data))\#组合IP+端口，如：61.135.217.7:80

return \[":".join(i) for i inzip(ip,port)\]\#打开页面，执行评分行为

def do\_dz(code=0,ips=\[\]):\#点赞，如果代理IP不可用造成刷评分失败，则会自动换一个代理IP后继续刷评分

try:\#随机选取一个ip

ip =choice(ips)except:returnFalseelse:

proxies=\{"http":ip,

headers\_=\{"Accept":"\*/\*","Accept-Encoding":"gzip, deflate, sdch","Accept-Language":"zh-CN,zh;q=0.8,en;q=0.6","Referer":"https://best.zhaopin.com/","User-Agent":choice(user\_agent),

\}\#用浏览器的开发者工具跟踪评分事件传输的参数值

datas = \{'bestid': 6030, 'score': '5,5,5,5,5,5','source': 'best'\}try:\#评分请求url

url\_dz = "https://best.zhaopin.com/API/ScoreCompany.ashx"

\#执行评分行为(发送请求)

r\_dz = requests.post(url\_dz,headers=headers\_,data=datas,proxies=proxies)exceptrequests.exceptions.ConnectionError:print("Connection Error")if notips:print("not ip")

sys.exit()\#删除不可用的代理IP

if ip inips:

ips.remove(ip)\#重新请求URL

get\_url(code,ips)else:\#获取当前时间

date = datetime.datetime.now().strftime('%H:%M:%S')print(u"第%s次 \[%s\] \[%s\]：评分%s (剩余可用代理IP数：%s)" %(code,date,ip,r\_dz.text,len(ips)))if \_\_name\_\_ == '\_\_main\_\_':

ips=\[\]\#python3把xrange()与rang()e整合为一个range()

for i in range(5000):\#每隔1000次重新获取一次最新的代理IP

if i % 1000 ==0:

ips.extend(get\_ip\_list("2"))\#启用线程，隔2秒产生一个线程

t1 = threading.Thread(target=do\_dz,args=(i,ips))

t1.start()\#time.sleep的最小单位是毫秒

time.sleep(2)