#Python&requests=＞入门实战案例篇

#　用法一：requestst

案例一

import requests

# 爬取百度的页面源代码

url = "http://www.baidu.com"
resp = requests.get(url)
resp.encoding = "utf-8"
print(resp.text)  # 拿到百度页面源代码

上篇案例是调用lib库来爬取百度网页信息，跟这次会有差异，其它略略……

案例二

import requests

content = input("请输入你要检索的内容:")
url = f"https://www.sogou.com/web?query={content}"  
# url = "https://www.sogou.com/web?query="
headers = {
    # 添加一个请求头信息。 UA
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}
# 处理一个小小的反爬
resp = requests.get(url, headers=headers)
# print(resp.text)
print(resp.json())
print(resp.request.headers) # 可以查看到请求头信息

图片说明：

案例三

import requests
import json

url = "https://fanyi.baidu.com/sug" # 网址

data = {
    "kw":input("请输入一个单词:")
}
resp = requests.post(url,data=data)  # 发送请求

# print(resp.text)#text 拿到的是文本字符串  
print(resp.json()['data']) # json 拿到的是字典json数据

运行结果：

和网页上的信息对比

案例四

import requests

# url = "https://movie.douban.com/j/chart/top_list"
# url = "https://movie.douban.com/tag/#/?sort=U&range=0,10&tags=%E5%89%A7%E6%83%85,%E7%BB%BC%E8%89%BA"

url = "https://movie.douban.com/chart"
data ={

        "channel": "notification:user:253044743",
        "auth": "253044743_1643091007:ce03f9d9f2e9f941f6052a7ca79b098dbeea74b6"

}

# data = {  # 一堆参数下
#         "sort": "U"
#         "range": "0:10"
#         "tags": ""
#         "start": "0"
#         "genres": "剧情"
#
# }


# data = {
#         "type": "13",
#         "interval_id":"100:90",
#         "action":"",
#         "start": "0",
#         "limit": "20"
# }

headers = {

        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"

}

resp = requests.get(url,params=data,headers=headers) # 处理一个小小的反爬
# print(resp.text)
print(resp.json())  
print(resp.request.url) 

#　https://movie.douban.com/j/chart/top_list 爬取此网站容易被封ip，需要用到代理待后续，请求次数过多的情况下…………