python爬虫---requests库的用法详解

import requests
response = requests.get('http://www.baidu.com')
print(response.status_code) # 打印状态码
print(response.url) # 打印请求url
print(response.headers) # 打印头信息
print(response.cookies) # 打印cookie信息
print(response.text) #以文本形式打印网页源码
print(response.content) #以字节流形式打印

import requests

requests.get('http://httpbin.org/get')
requests.post('http://httpbin.org/post')
requests.put('http://httpbin.org/put')
requests.delete('http://httpbin.org/delete')
requests.head('http://httpbin.org/get')
requests.options('http://httpbin.org/get')

import requests

response = requests.get('http://httpbin.org/get')
print(response.text)

import requests

response = requests.get(http://httpbin.org/get"" src="/UploadFiles/2021-04-08/202009282127463.png">

另一种先将参数填写在dict中，发起请求时params参数指定为dict


import requests

data = {
  'name': 'tom',
  'age': 20
}

response = requests.get('http://httpbin.org/get', params=data)
print(response.text)


结果同上
解析json


import requests

response = requests.get('http://httpbin.org/get')
print(response.text)
print(response.json()) #response.json()方法同json.loads(response.text)
print(type(response.json()))


结果

简单保存一个二进制文件
二进制内容为response.content


import requests

response = requests.get('http://img.ivsky.com/img/tupian/pre/201708/30/kekeersitao-002.jpg')
b = response.content
with open('F://fengjing.jpg','wb') as f:
  f.write(b)


为你的请求添加头信息


import requests
heads = {}
heads['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'
 response = requests.get('http://www.baidu.com',headers=headers)


使用代理
同添加headers方法，代理参数也要是一个dict
这里使用requests库爬取了IP代理网站的IP与端口和类型
因为是免费的，使用的代理地址很快就失效了。


import requests
import re

def get_html(url):
  proxy = {
    'http': '120.25.253.234:812',
    'https' '163.125.222.244:8123'
  }
  heads = {}
  heads['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'
  req = requests.get(url, headers=heads,proxies=proxy)
  html = req.text
  return html

def get_ipport(html):
  regex = r'<td data-title="IP">(.+)</td>'
  iplist = re.findall(regex, html)
  regex2 = '<td data-title="PORT">(.+)</td>'
  portlist = re.findall(regex2, html)
  regex3 = r'<td data-title="类型">(.+)</td>'
  typelist = re.findall(regex3, html)
  sumray = []
  for i in iplist:
    for p in portlist:
      for t in typelist:
        pass
      pass
    a = t+','+i + ':' + p
    sumray.append(a)
  print('高匿代理')
  print(sumray)


if __name__ == '__main__':
  url = 'http://www.kuaidaili.com/free/'
  get_ipport(get_html(url))


结果：

基本POST请求：


import requests

data = {'name':'tom','age':'22'}

response = requests.post('http://httpbin.org/post', data=data)



获取cookie


#获取cookie
import requests

response = requests.get('http://www.baidu.com')
print(response.cookies)
print(type(response.cookies))
for k,v in response.cookies.items():
  print(k+':'+v)


结果：

会话维持


import requests

session = requests.Session()
session.get('http://httpbin.org/cookies/set/number/12345')
response = session.get('http://httpbin.org/cookies')
print(response.text)


结果：

证书验证设置


import requests
from requests.packages import urllib3

urllib3.disable_warnings() #从urllib3中消除警告
response = requests.get('https://www.12306.cn',verify=False) #证书验证设为FALSE
print(response.status_code)打印结果：200


超时异常捕获


import requests
from requests.exceptions import ReadTimeout

try:
  res = requests.get('http://httpbin.org', timeout=0.1)
  print(res.status_code)
except ReadTimeout:
  print(timeout)


异常处理
在你不确定会发生什么错误时，尽量使用try...except来捕获异常
所有的requests exception：
Exceptions


import requests
from requests.exceptions import ReadTimeout,HTTPError,RequestException

try:
  response = requests.get('http://www.baidu.com',timeout=0.5)
  print(response.status_code)
except ReadTimeout:
  print('timeout')
except HTTPError:
  print('httperror')
except RequestException:
  print('reqerror')


25行代码带你爬取4399小游戏数据


import requests
import parsel
import csv
f = open('4399游戏.csv', mode='a', encoding='utf-8-sig', newline='')

csv_writer = csv.DictWriter(f, fieldnames=['游戏地址', '游戏名字'])
csv_writer.writeheader()
for page in range(1, 106):
  url = 'http://www.4399.com/flash_fl/5_{}.htm'.format(page)
  headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'
  }
  response = requests.get(url=url, headers=headers)
  response.encoding = response.apparent_encoding
  selector = parsel.Selector(response.text)
  lis = selector.css('#classic li')
  for li in lis:
    dit ={}
    data_url = li.css('a::attr(href)').get()
    new_url = 'http://www.4399.com' + data_url.replace('http://', '/')
    dit['游戏地址'] = new_url
    title = li.css('img::attr(alt)').get()
    dit['游戏名字'] = title
    print(new_url, title)
    csv_writer.writerow(dit)
f.close()