爬蟲實戰爬取58同城房源信息

import requests from lxml import etree if __name__ == '__main__': #爬取到頁面源碼數據 url='https://su.58.com/ershoufang/' headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36' } page_text=requests.get(url=url,headers=headers).text tree=etree.HTML(page_text) #數據解析 #存儲li標簽對象 li_list=tree.xpath('//ul[@class="house-list-wrap"]/li') #這里class屬性值應該是雙引號 "" fp= open('./58.txt','w',encoding='utf-8') for li in li_list: #頁面數據局部解析 title=li.xpath('./div[2]/p/span/text()')[0] print(title) fp.write(title+'\n')