import requests
from lxml import etree
url = 'http://www.boxofficecn.com/boxoffice2019'
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.46"}
resp = requests.get(url,headers=headers)
#print(resp.text)查看发现爬取了页面源代码
page = etree.HTML(resp.text)
trs = page.xpath("//table/tbody/tr")[1:-1]
#print(trs)
for tr in trs:
num = tr.xpath('./td[1]/text()')
year = tr.xpath('./td[2]/text()')
name = tr.xpath('./td[3]/text()')
money = tr.xpath('./td[4]/text()')
if name:
"".join(name) # 这是处理不正常数据的合理方案
print(num, year, name, money)
10-18
03-06
“相关推荐”对你有帮助么?
-
非常没帮助
-
没帮助
-
一般
-
有帮助
-
非常有帮助
提交