python商业爬虫项目网站_<爬虫>商业爬虫

class RequestSpider(object):

def __init__(self):

url = "https://www.yaozh.com/login"

headers = {

'User-Agent': 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser) ',

# 'Cookie':'',

}

# 保存Cookie

session = requests.Session()

# 代理

proxy = {

# 'http': '117.88.5.125:3000',

# 'https':'117.88.176.110:3000',

}

login_form_data = {

'username': '',

'pwd': '',

'formhash': '',

'backurl': '',

}

# 忽略证书认证，登录

self.response = session.post(url=url, data=login_form_data, headers=headers, verify=False)

# 用保存的cookie登录

url = 'https://www.yaozh.com/member/'

self.data = session.get(url=url,headers=headers,verify=False).content.decode('utf-8')

# self.response = requests.get(url=url, proxies=proxy, headers=headers, verify=False)

def run(self):

# 1.请求头

request_headers = self.response.request.headers

print(request_headers)

# 2.响应头

response_headers = self.response.headers

print(response_headers)

# 3.响应状态码

code = self.response.status_code

print(code)

# 4.请求的cookie

request_cookie = self.response.request._cookies

print(request_cookie)

# 5.响应的cookie

response_cookie = self.response.cookies

print(response_cookie)

# 6.数据

# data = self.response.content.decode('utf-8')

data = self.data

print(data)

with open('yaozhi.html', 'w', encoding='utf-8') as f:

f.write(data)

RequestSpider().run()