python学习—第三节练习项目：爬取租房信息

问题

question.png

代码

from bs4 import BeautifulSoup
import requests

def gender_get(classname):
    if(classname) == ['member_boy_ico']:
        return 'boy'
    else:
        return 'girl'

def wb_analyse(url):
    wb_data = requests.get(url)
    soup = BeautifulSoup(wb_data.text, 'lxml')
    titles = soup.select('div.pho_info > h4 > em')
    addresses = soup.select('div.pho_info > p > span.pr5')
    rents = soup.select('div.day_l > span')
    imgs = soup.select('#curBigImage')
    ownerimgs = soup.select('div.js_box.clearfix > div.member_pic > a > img')
    ownnames = soup.select('div.js_box.clearfix > div.w_240 > h6 > a')
    genders = soup.select('div.js_box.clearfix > div.w_240 > h6 > span')

    for title, address, rent, img, ownerimg, ownname, gender in zip(titles, addresses, rents, imgs, ownerimgs, ownnames,
                                                                    genders):
        data = {
            'title': title.get_text(),
            'address': address.get_text(),
            'rent': rent.get_text(),
            'img': img.get('src'),
            'ownerimg': ownerimg.get('src'),
            'ownname': ownname.get_text(),
            'gender': gender_get(gender.get('class')),
        }
        print(data)

def url_get(wbpage):
    wbdata = requests.get(wbpage)
    soup = BeautifulSoup(wbdata.text,'lxml')
    links = soup.select('#page_list > ul > li > a')
    for link in links:
        urlwb = link.get('href')
        wb_analyse(urlwb)

urls = ["http://bj.xiaozhu.com/search-duanzufang-p{}-0/".format(number) for number in range(1,2)]

for single_url in urls:
    url_get(single_url)

总结

1. 一开始试图发现每一个链接的规律，后来发现其实链接可以从网页中爬取
2. 关于性别的判定，一开始不会取class中的内容，后来发现和图片的‘src’是一样的取法