用python爬取網(wǎng)頁(yè)表格數(shù)據(jù)，供大家參考，具體內(nèi)容如下

from bs4 import BeautifulSoup import requests import csv import bs4   #檢查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('無(wú)法鏈接服務(wù)器！！！')   #爬取資源 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)   #保存資源 def save_contents(urlist):  with open("D:/2016年中國(guó)企業(yè)500強(qiáng)排行榜.csv",'w') as f:   writer = csv.writer(f)   writer.writerow(['2016年中國(guó)企業(yè)500強(qiáng)排行榜'])   for i in range(len(urlist)):    writer.writerow([urlist[i][1],urlist[i][3],urlist[i][5]]) def main():  urli = []  url = "http://www.maigoo.com/news/463071.html"  rs = check_link(url)  get_contents(urli,rs)  save_contents(urli)  main() 

以上就是本文的全部?jī)?nèi)容，希望對(duì)大家的學(xué)習(xí)有所幫助，也希望大家多多支持武林站長(zhǎng)站。