18-xpath实战--爬取猪八戒网

https://beijing.zbj.com/search/f/?type=n&kw=saas

import requests
from lxml import html
etree = html.etree

url = "https://beijing.zbj.com/search/f/?type=n&kw=saas"

resp = requests.get(url)

html = etree.HTML(resp.text)

# 获取所有的div
divs = html.xpath("/html/body/div[6]/div/div/div[2]/div[5]/div[1]/div")

# 遍历所有的div
for div in divs:
    company = div.xpath("./div/div/a[1]/div/p/text()")[1].strip("\n\n")
    location = div.xpath("./div/div/a[1]/div/div/span/text()")[0]
    title = div.xpath("./div/div/a[2]/div[2]/div[2]/p/text()")[0]
    price = div.xpath("./div/div/a[2]/div[2]/div[1]/span[1]/text()")[0].strip("¥")
    print(company)