爬虫之requests库的使用

get基本请求

响应对象的属性:

# 获取响应对象中的内容是str格式
text
# 获取响应对象中的内容是二进制格式的
content
# 获取响应状态码
status_code
# 获取响应头信息
headers
# 获取请求的url
url

import requests
url = "https://www.cnblogs.com/songzhixue/p/10717975.html"
# 获得一个响应对象
response = requests.get(url=url)
# 调用响应对象中的text属性获取请求结果为字符串形式
print(response.text)

带参数的get请求

方式一:

import requests
url = "http://www.baidu.com/s?wd=周杰伦"
# requests模块可以自动将url中的汉字进行转码
response = requests.get(url).text
with open("./zhou.html","w",encoding="utf-8") as fp:
    fp.write(response)

方式二:

将参数以字典的形式传给params参数

import requests
choice = input("请输入搜索条件>>>:").strip()
params = {
    "wd":choice
}
# https://www.baidu.com/s?wd=周杰伦
url = "http://www.baidu.com/s?"
# 带参数的get请求
response = requests.get(url,params)
# 获取响应状态码
response.status_code

添加请求头信息

请求头以字典的方式传给headers参数

import requests
choice = input("请输入搜索条件>>>:").strip()
params = {
    "wd":choice
}
# https://www.baidu.com/s?wd=周杰伦
url = "http://www.baidu.com/s?"
# 封装请求头信息
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
}
# 带参数的get请求
response = requests.get(url,params,headers=headers)
# 获取响应状态码
response.status_code

post请求

豆瓣登录

开发者抓包工具抓取post请求的登录信息

基于Ajax的get请求

### 抓取豆瓣影评###
import json
import requests
# url = "https://movie.douban.com/j/search_subjects?type=movie&tag=%E7%83%AD%E9%97%A8&sort=recommend&page_limit=20&page_start=20"
# 获取ajax的请求网址(基于ajax的get请求)
url = 'https://movie.douban.com/j/search_subjects?'
# 自定义请求头
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
}
# 构建请求参数
params = {
    'type': 'movie',
    'tag': '热门',
    'sort': 'recommend',
    'page_limit': '100',   # 显示多少数据
    'page_start': '1',      # 从第几页开始显示
}
# 请求目标url
response = requests.get(url=url,params=params,headers=headers)
# 拿到响应数据,json格式的字符串
json_str = response.text
# 对响应数据反序列化得到字典
code = json.loads(json_str)
# 在字典中取出想要的数据
for dic  in code["subjects"]:
    rate = dic["rate"]
    title = dic["title"]
    print(title,rate)

基于Ajax的post请求

### 抓取肯德基餐厅位置信息###
import json
import requests
url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword'
data = {
    'cname': '',
    'pid': '',
    'keyword': '上海',# 查询城市
    'pageIndex':'1',  # 显示第几页的数据
    'pageSize': '10', # 一页显示多少数据
}
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
}
response = requests.post(url=url,data=data,headers=headers)
response.text

使用代理

import requests
# www.goubanjia.com
# 快代理
# 西祠代理
url = "http://www.baidu.com/s?wd=ip"
prox = {
    "http":"39.137.69.10:8080",
    "http":"111.13.134.22:80",
}
# 参数proxies
response = requests.get(url=url,proxies=prox).text
with open("./daili.html","w",encoding="utf-8") as fp:
    fp.write(response)
    print("下载成功")