import requests
from lxml import etree
headers = {'user-agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
def download(url):
reponse = requests.get(url,headers = headers)
reponse.encoding = 'gbk'
text = reponse.text
html = etree.HTML(text)
results = html.xpath('//*[@class=\'piclist longList\']//a[@href!=\'/article/\']//text()')
for line in results:
print(line)
duanzs = html.xpath('//*[@class=\'piclist longList\']//div[@class=\'f18 mb20\']//text()')
for linedata in duanzs:
print(linedata.strip())
print('*'*20)
download("https://www.neihan8.com/article/list_5_2.html")
BaiduShurufa_2019-1-18_22-30-43.png
