python 爬取链家

时间:2024-08-08 12:04:32
import json

import  requests
from lxml import etree
from time import sleep url = "https://sz.lianjia.com/ershoufang/rs/"
headers = {
"User-Agent":"",
"Refer":"https://sz.lianjia.com/ershoufang/pg2/"
}
resp = requests.get(url,headers=headers) base_url = "https://sz.lianjia.com/ershoufang/pg{}/"
html = etree.HTML(resp.text)
data = html.xpath('//*[@id="content"]//div[@class="page-box fr"]/div/@page-data')
data = json.loads(data[0])
totalPage = data['totalPage']
curPage = data['curPage'] def get_data(url):
list = []
resp = requests.get(url, headers=headers)
html = etree.HTML(resp.text)
ul = html.xpath('.//ul[@class="sellListContent"]/li')
for li in ul:
face = li.xpath('./a/img/@src')
title = li.xpath('.//div[@class="title"]/a/text()')
position = li.xpath('.//div[@class="positionInfo"]/a/text()')
house_info = li.xpath('.//div[@class="houseInfo"]/text()')
follow_info = li.xpath('.//div[@class="followInfo"]/text()')
price = li.xpath('.//div[@class="priceInfo"]/div[@class="totalPrice"]/span/text()')
unit_price = li.xpath('.//div[@class="priceInfo"]/div[@class="unitPrice"]/span/text()')
tag = li.xpath('.//div[@class="tag"]//span/text()')
content = {}
content["face"] = face[0]
content["title"] = title[0]
content["position"] = position[0]
content["house_info"] = house_info[0]
content["follow_info"] = follow_info[0]
content["price"] = price[0]
content["unit_price"] = unit_price[0]
if len(tag) >=1 and tag[0] is not None:
content['tag'] = tag[0]
list.append(content)
return list totalList = []
for i in range(1,totalPage+1):
url = base_url.format(i)
print("crawl url " + url)
cur_list = get_data(url)
print(cur_list)
totalList = totalList + cur_list url = base_url.format(1) print(totalList)

python 爬取链家