展开全部
你好!
可以通过lxml来获取指定标签的内容。#安装e69da5e6ba903231313335323631343130323136353331333431353932lxml
pip install lxmlimport requests
from lxml import html
def getHTMLText(url):
....
etree = html.etree
root = etree.HTML(getHTMLText(url))
#这里得到一个表格内tr的集合
trArr = root.xpath("//div[@class='news-text']/table/tbody/tr");
#循环显示tr里面的内容
for tr in trArr:
rank = tr.xpath("./td[1]/text()")[0]
name = tr.xpath("./td[2]/div/text()")[0]
prov = tr.xpath("./td[3]/text()")[0]
strLen = 22-len(name.encode('GBK'))+len(name)
print('排名:{:<3}, 学校名称:{:
希望对你有帮助!