day20-Spider02

1. 批量下载图片作业

import requests
import json

for x in range(1, 10):
    URL = 'https://api.ixiaowai.cn/api/api.php?return=json'
    resp = requests.get(url=URL)
    resp.encoding = 'utf-8-sig'
    # print(resp.text,type(resp.text))
    # 序列化
    data = json.loads(resp.text)
    # print(data)
    resp1 = requests.get(url=data['imgurl'])
    # print(resp1.content)

    with open(f'imgs/{
     x}.jpg', 'wb') as f:
        f.write(resp1.content)

2. 正则表达式匹配页面内容

import requests
import re
import csv

# 打开文件
f = open('中国新闻网.csv', 'w', encoding='utf-8', newline='')
# 将csv中的写方法赋给一个变量
writer = csv.writer(f)
# 写入标题
writer.writerow(['新闻类型', '新闻链接', '新闻标题', '新闻时间'])

for i in range(1, 11):
    # f'{i}' -> f-字符串、格式化