爬取猎取网药品说明书

import requests
import codecs
from lxml import html
headers={
    'Host':'www.liequ.net',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
}
for i in range(1,9445):
    url='https://www.liequ.net/yaopin/{}.html'.format(i)
    r=requests.get(url,headers,verify=False)
    status=r.status_code
    if status==200:
        print('完成{}页'.format(i))
        s = requests.session()
        s.keep_alive = False
        r.encoding = 'utf-8'
        content = html.fromstring(r.text)
        name = content.xpath('//div[@id="liequleft"]/div/div[2]/div[1]/h2/text()')
        describe=content.xpath('//td[1]/text()')[9:]
        output='{}\t{}\n'.format(name,describe)
        f=codecs.open('liequ.xls','a+')
        f.write(output)
        f.close()
    else:
        print('第{}页失败'.format(i))