Python爬虫1----房源信息

任务描述

爬取300个房源信息，每页具体信息如下

---

Python代码

#-*- coding: UTF-8 -*-
# 20170217:work well
from bs4 import BeautifulSoup
import requests

# 形成小猪主页上前10页的网址
urls = ['http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(str(i)) for i in range(1, 11, 1)]

# 性别不同，标签的class属性内容不同，通过这个差异区分房东性别
def get_lorder_sex(class_name):
    if class_name == ['member_ico']:
        return '男'
    elif class_name == ['member_ico1']:
        return '女'

#对每一页上的具体信息进行解析
def get_attar(url):
    web_data = requests.get(url)
    soup = BeautifulSoup(web_data.text, 'lxml')
    titles = soup.select('div.pho_info > h4 > em')
    locations = soup.select('div.pho_info > p > span')
    prices = soup.select('div.day_l > span')
    images = soup.select('div.pho_show_big > div > img')
    lorder_names = soup.select('div.w_240 > h6 > a')
    lorder_images = soup.select('div.member_pic > a > img')
    lorder_genders = soup.select('div.member_pic > div')
    for title, location, price, image, lorder_name, lorder_image, gender in zip(titles, locations, prices, images, lorder_names, lorder_images, lorder_genders):
        data = {
            'title': title.get_text(),
            'location': location.get_text(),
            'price': price.get_text(),
            'image': image.get('src'),
            'lorder_name': lorder_name.get_text(),
            'lorder_image': lorder_image.get('src'),
            "gender": get_lorder_sex(gender.get("class"))
        }
        print data

#10个主页中，每一个主页又有很多小页：上面记录了待租房的具体信息
for url in urls:
    web_data = requests.get(url)
    soup = BeautifulSoup(web_data.text, 'lxml')
    url_links = soup.select('a.resule_img_a')
    for url_link in url_links:
        get_attar(url_link.get('href'))

---

结果展示

这里仅截取其中两个房源信息

---

不足之处

Pycharm的控制台中，对中文汉字，只能显示其字符编码，未能显示中文