[Python 练习爬虫] XPATH基础语法

import requests
from lxml import etree

for i in range(1, 21):
    url = "http://www.xxx.com/topic/tv/page/{}".format(i)
    req = requests.get(url).content

    html = etree.HTML(req)

    # 提取文本
    text = html.xpath(
        ‘/html/body/section/div[1]/div/article[*]/header/h2/a/text()‘)
    for each in text:
        print(1,each)

    # 提取链接
    # link = html.xpath(‘//a/@href‘)
    # for i in link:
    #     print(i)