实战计划0430-石头的练习作业
练习的要求
课程要求抓取的内容：
实现效果如下
运行结果
相关代码
__author__ = 'daijielei'
'''
11课时练习，从小猪短租处抓取一堆租房详情
'''
from bs4 import BeautifulSoup #解析html文档用
import requests #抓取html页面用
import time
#urls用来制定抓取范围，header该处无用处
header = {
'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.110 Safari/537.36',
'Host':'bj.xiaozhu.com'
}
#getlist用来抓取对应网页上的每个列表的跳转url
#测试用url = "http://bj.xiaozhu.com/search-duanzufang-p1-0/"
def getlist(url):
webData = requests.get(url,headers=header)
soup = BeautifulSoup(webData.text,'lxml')
houselists = soup.select('ul > li > a')
for houselist in houselists:
listUrl = str(houselist.get('href'))
if(listUrl.find('http://bj.xiaozhu.com/fangzi/')!=-1):#确认链接内容为详情页，则进行详情页信息抓取
#print(listUrl)
getInfoPage(listUrl)
#getInfoPage用来抓取详情页里的相关信息，如标题、地址、金额、房屋图片、拥有人图片等等
#测试用url = "http://bj.xiaozhu.com/fangzi/525041101.html"
def getInfoPage(url):
webData = requests.get(url,headers=header)
soup = BeautifulSoup(webData.text,'lxml')
time.sleep(2)
titles = soup.select('body > div.wrap.clearfix.con_bg > div.con_l > div.pho_info > h4 > em')
address = soup.select('body > div.wrap.clearfix.con_bg > div.con_l > div.pho_info > p > span.pr5')
pays = soup.select('#pricePart > div.day_l > span')
houseimages = soup.select('#curBigImage')
ownerimages = soup.select('#floatRightBox > div.js_box.clearfix > div.member_pic > a > img')
ownernames = soup.select('#floatRightBox > div.js_box.clearfix > div.w_240 > h6 > a')
ownerSexs = soup.select('#floatRightBox > div.js_box.clearfix > div.w_240 > h6 > span')
for title,addres,pay,houseimage,ownerimage,ownername,ownerSex in zip(titles,address,pays,houseimages,ownerimages,ownernames,ownerSexs):
data = {
'title':title.get_text(),
'addres':addres.get_text(),
'pay':pay.get_text(),
'houseimage':houseimage.get('src'),
'ownerimage':ownerimage.get('src'),
'ownername':ownername.get_text(),
'ownerSex':'female'
}
if('member_boy_ico' in str(ownerSex['class'])):#该处用来判断是男性还是女性，男性是通过标签来区分
data['ownerSex'] = "male"
print(data)
def startCatch():
urls = ["http://bj.xiaozhu.com/search-duanzufang-p{}-0/".format(str(i)) for i in range(1,3,1)]
for url in urls:
getlist(url)
#入口，该语句只有直接执行时会被调用
if __name__ == '__main__':
startCatch()
笔记、想法、总结
1、这个代码是之前写的了，所以显得比较乱，尤其是抓取的部分现在写的话我就不会用这种写法了
2、这里面主要有3个函数，功能还是比较清晰，先爬取列表，再进列表里去爬取数据：
def startCatch(): #用来便利列表，会调用getlist
def getlist(url): #用来抓取列表的数据，会调用getInfoPage
def getInfoPage(url):#抓取详情页的数据
3、比较难抓的数据只有性别信息，因为不是直接能抓取的值，而是要做一下判断：
在html中为如下,是用span里的class来区别男女，男为member_boy_ico、女为member_girl_ico：
<h6>
<a class="lorder_name" href="http://www.xiaozhu.com/fangdong/617264400/" title="ocheese" target="_blank">ocheese</a>
<span class="member_girl_ico"></span>
</h6>
代码中就是做一下判断即可
if('member_boy_ico' in str(ownerSex['class'])):#该处用来判断是男性还是女性，男性是通过标签来区分
data['ownerSex'] = "male"
