爬虫作业1

作业1

import requests
import json
for i in range(10):
    URL = 'https://api.ixiaowai.cn/api/api.php?return=json'
    resp = requests.get(url=URL)
    resp.encoding = 'utf-8-sig'
    data = json.loads(resp.text)
    print(data, type(data))
    img_url = data['imgurl']
    print(img_url)
    img_resp = requests.get(url=img_url)
    name = i
    with open(f'{name}.jpg','wb') as f1:
        f1.write(img_resp.content)


作业2

import requests
from re import search, findall, finditer
url = 'https://www.chinanews.com.cn/scroll-news/news1.html'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36'
}

resp = requests.get(url=url,headers=headers)
resp.encoding = 'UTF-8'
title = findall(r'<div class="dd_lm">\[<a href=.