Python实战计划学习笔记（4）网页解析作业

第一周第三节练习项目

总结

• 使用BeautifulSoup库可以很方便地处理网页
• 基本套路是用select确定元素位置，get()和get_text()方法提取数据
• 使用User-Agent和Cookie可以”欺骗“服务器
• 爬取网页时要注意通过延时来避免暴露身份

任务

（1）爬取小猪短租网站上一条房源信息
（2）爬取小猪短租网站上300条房源信息

任务1代码

from bs4 import BeautifulSoup
import requests
import time

url='http://bj.xiaozhu.com/fangzi/3686435130.html'

web_data = requests.get(url)
soup = BeautifulSoup(web_data.text,'lxml')
titles = soup.select('div.pho_info > h4 > em')
addresses = soup.select('span.pr5')
prices = soup.select('div.day_l')
room_photos = soup.select('div.pho_show_l > div > div:nth-of-type(2) > img')
lord_photos = soup.select('div.member_pic > a > img')
lord_names = soup.select('a.lorder_name')
lord_genders = soup.select('div.js_box.clearfix > div.w_240 > h6 > span')
for title,address,price,room_photo,lord_photo,lord_name,lord_gender in zip(titles,addresses,prices,room_photos,lord_photos,lord_names,lord_genders):
    if lord_gender.get('class')[0] == 'member_girl_ico':
        lord_gender = '美女'
    else:
        lord_gender = '帅哥'
    data = {
        'title':title.get_text(),
        'address':address.get_text().split('\n')[0],
        'price':price.get_text()[1:],
        'room_photo':room_photo.get('src'),
        'lord_photos':lord_photo.get('src'),
        'lord_name':lord_name.get_text(),
        'lord_gender':lord_gender
    }
    print(data)

任务1运行结果

1.jpg

任务2代码

from bs4 import BeautifulSoup
import requests
import time

urls = ['http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(str(i)) for i in range(1,14,1)]

def get_page(url):
    link_list=[]
    web_data = requests.get(url)
    soup = BeautifulSoup(web_data.text,'lxml')
    links = soup.select('ul > li > div.result_btm_con.lodgeunitname')
    for link in links:
        link_url = link.get('detailurl')
        #print (link_url)
        link_list.append(link_url)
    return(link_list)

def get_info_from_page(url):
    web_data = requests.get(url)
    soup = BeautifulSoup(web_data.text, 'lxml')
    titles = soup.select('div.pho_info > h4 > em')
    addresses = soup.select('span.pr5')
    prices = soup.select('div.day_l')
    room_photos = soup.select('div.pho_show_l > div > div:nth-of-type(2) > img')
    lord_photos = soup.select('div.member_pic > a > img')
    lord_names = soup.select('a.lorder_name')
    lord_genders = soup.select('div.js_box.clearfix > div.w_240 > h6 > span')
    for title, address, price, room_photo, lord_photo, lord_name, lord_gender in zip(titles, addresses, prices,
                                                                                     room_photos, lord_photos,
                                                                                     lord_names, lord_genders):
        if lord_gender.get('class')[0] == 'member_girl_ico':
            lord_gender = '美女'
        else:
            lord_gender = '帅哥'
        data = {
            'title': title.get_text(),
            'address': address.get_text().split('\n')[0],
            'price': price.get_text()[1:],
            'room_photo': room_photo.get('src'),
            'lord_photos': lord_photo.get('src'),
            'lord_name': lord_name.get_text(),
            'lord_gender': lord_gender
        }
    return(data)


links_to_read=[]
room_info=[]
for single_url in urls:
    links_to_read = links_to_read + get_page(single_url)
    time.sleep(4)

print('共爬取',len(links_to_read),'条房源信息')

for crawl_url in links_to_read:
    room_info.append(get_info_from_page(crawl_url))
    time.sleep(4)

print(room_info)

任务2运行结果

1.jpg