import requests
import re
from random import randint
def CrawlerHouse(): url = "https://www.danke.com/room/hz" headers = { 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50' } res = requests.get(url,headers=headers[randint(0, len(headers)-1)]) res.encoding = "utf-8" infolist = re.findall('<div class="r_lbx_cena">(.*?)</div>', res.text,re.S) i = 1 for one in infolist: two = one.split('<span class="location">{0}</span>'.format(i)) two = ''.join(two) job = re.findall('>(.*?)</a>',two,re.S) job = ''.join(job).strip() print(job) i += 1 CrawlerHouse()
uj5u.com熱心網友回復：
把腳本用代碼類的插入，把目的描述清楚，更容易引來大佬解決，看著太亂了轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/81711.html