requests爬取扇贝单词

import requests,re

proxy={
    "HTTP": "113.3.152.88:8118",
    "HTTPS": "219.234.5.128:3128",
}

headers={
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
}

base_url="https://www.shanbay.com/wordlist/110521/232414/?page="
#url="https://www.shanbay.com/wordlist/110521/232414/?page=1"

def get_word():
    page=input("请输入获取第几页:")
    url = base_url+page
    response=requests.get(url,headers=headers,proxies=proxy)
    html=response.content.decode("utf-8")
    res = re.compile(r'<strong>(.*?)</strong>[\w\W]*?"span10">(.*?)</td>')
    ret = res.findall(html)
    return ret,page

def write_word(ret,page):
    file_name="扇贝单词第%s页.txt"%page
    with open(file_name, "w", encoding="utf-8") as fp:
        for i in ret:
            print(i[0] + "\t" + i[-1])
            fp.write(i[0] + "\t" + i[-1] + "\n")
    print(str(len(ret))+"个单词写完")


if __name__=="__main__":
    ret,page=get_word()
    write_word(ret,page)

不懂的可以看一下我上一篇写的博文

紧接上一个博客写了两个简单的requests爬取: https://blog.csdn.net/weixin_44185953/article/details/85722993.