# Chain new house reptiles ** ** goal today crawling latest region and the corresponding prices `` `Python Import Requests Import Re Import CSV class LianjiaSpider (Object): DEF __init__ (Self): self.url = ' HTTPS: // CQ .lianjia.com / ershoufang / PG {} / ' self.headers = { ' the User-- Agent ' : ' the Mozilla / 5.0 ' } # Get URL DEF the get_page (Self, URL): RES = requests.get (URL, headers = self.headers) HTML =res.content.decode() #直接调用解析函数 self.parse_page(html) #解析数据 def parse_page(self,html): pattern=re.compile('<div class="houseInfo"><span.*?data-el="region">(.*?)</a>.*?<div class="totalPrice"><span>(.*?)</span>',re.S) r_list=pattern.findall(html) self.write_page(r_list) #保存 def write_page(self,r_list): film_list=[] with open('lianjia.csv','a') as f: Writer = csv.writer (F) for R & lt in r_list: # the processed data is defined as a tuple T = (R & lt [0] .strip (), R & lt [. 1] + ' Wan ' ) film_list.append (T) writer.writerows (film_list) DEF main (Self): for page in Range (1,11 ): URL = self.url.format (page) self.get_page (URL) Print ( ' being printed pages {} ' .format ( Page)) IF the __name__ == ' __main__ ': spider=LianjiaSpider() spider.main() ```