【零基础学爬虫】第二章：3个xpath实战案例

1.爬取58二手房信息

需求：爬取58二手房中的房源信息（标题）https://bj.58.com/ershoufang/

发现爬取规律：

import requests
from lxml import etree
# 需求：爬取58二手房中的房源信息
if __name__ == "__main__":
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
    }
    # 爬取到页面源码数据
    url = 'https://bj.58.com/ershoufang/'
    page_text = requests.get(url=url,headers=headers).text

    # 数据解析
    tree = etree.HTML(page_text)
    # 存储的就是div标签对象
    div_list = tree.xpath('//section[@class="list"]/div[@class="property"]')
    # print(div_list)
    fp = open('58.txt','w',encoding='utf-8')
    for div in div_list:
        # 局部解析
        title = div.xpath('.//div[@class="property-content-title"]/h3/@title')[0]
        print(title)
        fp.write(title+'\n')

2.解析下载图片数据

需求：解析下载图片数据 http://pic.netbian.com/4kmeinv/

思路：先把每个图片的url和名称取出来，然后再进行保存

注意：图片名称可能会出现乱码的情况，代码中有两种解决方法，这两种其中必有一种可以解决，具体情况大家可以具体尝试。这里通用的处理方法可以使用。

import requests
from lxml import etree
import os
if __name__ == "__main__":
    url = 'http://pic.netbian.com/4kmeinv/'
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
    }
    response = requests.get(url=url,headers=headers)
    # 手动设定响应数据的编码格式
    # response.encoding = 'utf-8'
    page_text = response.text

    # 数据解析：src的属性值  alt属性
    tree = etree.HTML(page_text)
    li_list = tree.xpath('//div[@class="slist"]/ul/li')


    # 创建一个文件夹
    if not os.path.exists('./picLibs'):
        os.mkdir('./picLibs')

    for li in li_list:
        # 抓取图片url和图片名称
        img_src = 'http://pic.netbian.com'+li.xpath('./a/img/@src')[0]
        img_name = li.xpath('./a/img/@alt')[0]+'.jpg'
        # 通用处理中文乱码的解决方案
        img_name = img_name.encode('iso-8859-1').decode('gbk')

        # print(img_name,img_src)
        # 请求图片进行持久化存储
        img_data = requests.get(url=img_src,headers=headers).content
        img_path = 'picLibs/'+img_name
        with open(img_path,'wb') as fp:
            fp.write(img_data)
            print(img_name,'下载成功！！！')

3.解析城市名称

需求：解析城市名称 https://www.aqistudy.cn/historydata/

import requests
from lxml import etree
#项目需求：解析出所有城市名称https://www.aqistudy.cn/historydata/
if __name__ == "__main__":
    # headers = {
    #     'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
    # }
    # url = 'https://www.aqistudy.cn/historydata/'
    # page_text = requests.get(url=url,headers=headers).text
    #
    # tree = etree.HTML(page_text)
    # host_li_list = tree.xpath('//div[@class="bottom"]/ul/li')
    # all_city_names = []
    # #解析到了热门城市的城市名称
    # for li in host_li_list:
    #     hot_city_name = li.xpath('./a/text()')[0]
    #     all_city_names.append(hot_city_name)
    #
    # #解析的是全部城市的名称
    # city_names_list = tree.xpath('//div[@class="bottom"]/ul/div[2]/li')
    # for li in city_names_list:
    #     city_name = li.xpath('./a/text()')[0]
    #     all_city_names.append(city_name)
    #
    # print(all_city_names,len(all_city_names))

    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'
    }
    url = 'https://www.aqistudy.cn/historydata/'
    page_text = requests.get(url=url, headers=headers).text

    tree = etree.HTML(page_text)
    #解析到热门城市和所有城市对应的a标签
    # //div[@class="bottom"]/ul/li/          热门城市a标签的层级关系
    # //div[@class="bottom"]/ul/div[2]/li/a  全部城市a标签的层级关系
    a_list = tree.xpath('//div[@class="bottom"]/ul/li/a | //div[@class="bottom"]/ul/div[2]/li/a')
    all_city_names = []
    for a in a_list:
        city_name = a.xpath('./text()')[0]
        all_city_names.append(city_name)
    print(all_city_names,len(all_city_names))