Beautiful Soup 解析html表格示例

from bs4 import BeautifulSoup
import urllib.request
doc = urllib.request.urlopen(‘http://www.bkzy.org/Index/Declaration?intPageNo=1‘)
doc = doc.read().decode(‘utf-8‘)

soup = BeautifulSoup(doc, "html.parser")

school = 0
pro_code = 1
pro_name = 2
xuewei = 3
pdf = 4


# find_all 查到所有tr列表
for tr in soup.find_all(‘tr‘,):
　　# 在每个tr找td
    td = tr.find_all(‘td‘)
    try:
        print(‘%s_%s_%s_%s.pdf‘ % (
            td[school].text.strip(),
            td[pro_code].text.strip(),
            td[pro_name].text.strip(),
            td[xuewei].text.strip())
            ,td[pdf].find(‘a‘)[‘href‘])
    except IndexError as e:
        pass


参考文档 = ‘http://cuiqingcai.com/1319.html‘