1.get请求搜狗浏览器_处理一个UA反爬

import requests
content = input("请输入你要搜索的内容：")
url = f"https://www.sogou.com/web?query={content}"
headers = {
          # 添加一个请求头信息.UA
    "user-agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36"
}
# 处理一个反爬
a = requests.get(url,headers = headers)
print(a.text)

2.post请求百度翻译调用

import requests
url = "https://fanyi.baidu.com/sug"
data = {
    "kw" : input("请输入要翻译的汉字：")
}
resp = requests.post(url,data = data)
for i in resp.json()["data"]:
    print(i)

3.豆瓣电影排行榜名单获取1.0

import requests

url = "https://movie.douban.com/j/chart/top_list"
params = {
    "type": "13",
    "interval_id": "100:90",
    "action":"",
    "start":"0",
    "limit": "20"
}
headers = {
    # UA反爬
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36"
}
resp = requests.get(url,params = params,headers = headers)
# print(resp.json()[0]["rating"][0])
# print(resp.json()[0]["title"])
j = 0
for i in resp.json():
    a = "电影名称:"+ resp.json()[j]["title"]
    b = "评分:"+ resp.json()[j]["rating"][0]
    j+=1
    print(a,b)

4.豆瓣top250排行榜数据获取2.0

import requests
import re
f = open('doubantop250.csv',mode='w',encoding='utf-8')
headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36"
    }
shu = 0
j = 0
while 1:
    url = f"https://movie.douban.com/top250?start={shu}&filter="
    shuju = requests.get(url, headers=headers)
    shu+=25
    if shu > 275:
        break
    obj = re.compile(r'<div class="item">.*?<span class="title">(?P<nume>.*?)</span>.*?'
                     r'<div class="bd">.*?导演: (?P<daoyan>.*?) .*?<div class="star">.*?'
                     r"</span>.*?<span>(?P<pingjia>.*?)</span>", re.S)
    # 进行正则匹配
    shuju1 = obj.finditer(shuju.text)
    for i in shuju1:
        j += 1
        nume = i.group("nume")
        daoyan = i.group('daoyan')
        pingjia = i.group('pingjia')
        print(f"电影名称{j}：" + nume, "导演：" + daoyan, "评价数量：" + pingjia)
        f.write(f"电影名称{j}:{nume}, 导演： {daoyan}, 评价数量： {pingjia}\n")

f.close()
shuju.close()
print('完成')

5.优美图库图片爬取

import requests
from bs4 import BeautifulSoup
url = "http://www.umeituku.com/tags/siwa.htm"
resp = requests.get(url)
resp.encoding = "utf-8"
# print(resp.text)
main = BeautifulSoup(resp.text, "html.parser")
a = main.find_all("a", attrs={"class": "TypeBigPics"})
计数 = 0
for b in a:
    子链接 = b.get("href")
    name = b.text
    resp2 = requests.get(子链接)
    resp2.encoding = "utf-8"
    main2 = BeautifulSoup(resp2.text, "html.parser")
    a2 = main2.find("div", attrs={"class": "ImageBody"})
    dow = a2.find("img").get("src")
    dow_resp = requests.get(dow)
    with open(rf"C:\Users\xiazhimiao\Desktop\swmn\{name}.jpg", mode="wb") as f:
        f.write(dow_resp.content)
    print(f"下载完毕{计数}")
    计数+=1
resp.close()
resp2.close()

重要声明

本博客记录内容仅用来学习，无非法用途，如有不当之处，麻烦联系V：xia_12_13，删除内容。

Python爬虫学习经历_爬虫