import requests
from bs4 import BeautifulSoup
import time
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 '
'(KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
}
def judgment_sex(class_name):#判别房东男女的函数
if class_name==['member_ico1']:
return '女'
else:
return '男'
def get_links(url):#获取详细页
wb_data = requests.get(url, headers=headers)
soup = BeautifulSoup(wb_data.text, 'lxml')
links = soup.select('#page_list > ul > li> a ')
for link in links:
href = link.get('href')
get_info(href)
def get_info(url):#获取网页信息的函数
wb_data=requests.get(url,headers=headers)
soup=BeautifulSoup(wb_data.text,'lxml')
tittles=soup.select('div.pho_info > h4')
addresses=soup.select('span.pr5')
prices=soup.select('#pricePart > div.day_l > span')
imgs=soup.select('#floatRightBox > div.js_box.clearfix > div.member_pic > a > img')
names = soup.select('#floatRightBox > div.js_box.clearfix > div.w_240 > h6 > a')
sexs=soup.select('#floatRightBox > div.js_box.clearfix > div.member_pic > div')
for tittle,address,price,img,name,sex in zip(tittles,addresses,prices,imgs,names,sexs):
data={
'tittle':tittle.get_text().strip(),
'address':address.get_text().strip(),
'price':price.get_text(),
'img':img.get("src"),
'name':name.get_text(),
'sex':judgment_sex(sex.get("class"))
}
print(data)#打印信息
if __name__ == '__main__':#主入口
urls=['https://gz.xiaozhu.com/search-duanzufang-p{}-0/'.format(number) for number in range(1,4)]
for single_url in urls:
get_links(single_url)
time.sleep(2)#睡眠2秒
python爬虫实例小猪短租爬虫,运行后爬不到数据,求各位老板指点
- 写回答
- 好问题 0 提建议
- 关注问题
- 邀请回答
-
2条回答 默认 最新
木三136 2021-04-10 11:40关注该网站是使用ajax动态加载的,您使用get_links函数所获得的的网页源码是不完整的,所以什么都爬不到
您可以通过获取json文件来获得您需要的内容
本回答被题主选为最佳回答 , 对您是否有帮助呢?评论 打赏 举报解决 1无用