python3 爬表格数据

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/qq_35774189/article/details/86526240

数据网址：http://gaokao.xdf.cn/201812/10838484.html

https://www.maigoo.com/news/509088.html

代码段：

from bs4 import BeautifulSoup

import requests
import csv

#检查url地址  
def check_link(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print('无法链接服务器！！！')

#爬取资源  
def get_contents(ulist,rurl):
    soup = BeautifulSoup(rurl,'lxml')
    trs = soup.find_all('tr')
    for tr in trs:
        ui = []
        for td in tr:
            ui.append(td.string)
        ulist.append(ui)

#保存资源  
def save_contents(urlist):
    try:
        with open("500强数据.csv",'w') as f:
            writer = csv.writer(f)
            writer.writerow(['2018中国企业500强完整榜单'])
            for i in range(len(urlist)):
                writer.writerow([urlist[i][1],urlist[i][3],urlist[i][5]])
    except:
        pass

def main():
    urli = []
    url = "https://www.maigoo.com/news/509088.html"
    rs = check_link(url)
    get_contents(urli,rs)
    save_contents(urli)

main()

链接：https://pan.baidu.com/s/1DaNAh3BWVbo__KqheRKqXA   提取码：y075

同参考文章： https://blog.csdn.net/weixin_41059146/article/details/78605081

https://blog.csdn.net/weixin_42459037/article/details/84024839