第一次写 有很多毛病,没防封ip。。。没多线程 不过数据量不大凑活着用吧,代码如下:
from bs4 import BeautifulSoup
import requests
import time
import re
urls = ["{}/?PGTID=0d100000-000f-12db-512a-5598dd1c3104&ClickID=1".format(str(i)) for i in range(1,20)]
for url in urls:
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.106 Safari/537."}
response = (url,headers = headers)
web_data = ,"lxml")
allurl = web_data.select("body > wrap.clearfix > t.clearfix > div.listcon > div > dl > dd > h3 > a")
for i in allurl:
x = []
y = []
z = []
v = []
url = i.get("href")
#headers = {
# "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.106 Safari/537."}
response1 = (url, headers=headers)
web_data1 = , "lxml")
prices = web_data1.select("body > div.main > div.house-info.white-block.clearfix > div.house-primary-content-wrap.fr > ul > li.house-primary-content-li.house-primary-content-fir.clearfix > div > i > em")
payformants = web_data1.select("body > div.main > div.house-info.white-block.clearfix > div.house-primary-content-wrap.fr > ul > li.house-primary-content-li.house-primary-content-fir.clearfix > div > span")
rooms = web_data1.select("body > div.main > div.house-info.white-block.clearfix > div.house-primary-content-wrap.fr > ul > li:nth-of-type(2) > div")
address = web_data1.select("body > div.main > div.house-info.white-block.clearfix > div.house-primary-content-wrap.fr > ul > li:nth-of-type(4) > div")
peizhis = web_data1.select("body > div.main > div.house-info.white-block.clearfix > div.house-primary-content-wrap.fr > ul > li.house-primary-content-li.clearfix.broker-config > div > span")
pat = repile("s")
for peizhi in peizhis:
x.append(re.sub(pat, "", _text()))
l = " ".join(x)
for price in prices:
y.append(re.sub(pat, "", _text()))
for room in rooms:
z.append(re.sub(pat, "", _text()))
for addres in address:
v.append(re.sub(pat, "", _text()))
p = " ".join(v)
data = {"配置": l, "价格": y[0], "房型": z[0], "地址": p}
print(data)
本文发布于:2024-02-04 11:13:22,感谢您对本站的认可!
本文链接:https://www.4u4v.net/it/170705889255062.html
版权声明:本站内容均来自互联网,仅供演示用,请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系,我们将在24小时内删除。
留言与评论(共有 0 条评论) |