爬虫入门（二）

使用xpath解析数据

环境安装：

pip install lxml

解析原理：

　　1.获取网页源码数据

　　2.实例化一个etree对象，并切将页面源码数据加载到该对象中

　　3.调用该对象的xpath方法进行制定标签的定位

　　ps：xpath函数必须结合xpath表达式进行标签的定位和内容捕获

案例：

# 项目需求：解析58二手房的相关数据
import requests
from lxml import etree

url = 'https://bj.58.com/shahe/ershoufang/?PGTID=0d30000c-0047-e1d9-5baf-47db5897c065&ClickID=1'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36'
}

page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
li_list = tree.xpath("//ul[@class='house-list-wrap']/li")
fp = open('58.csv','w',encoding='utf8')
for li in li_list:
    title = li.xpath('./div[2]/h2/a/text()')[0]
    price = li.xpath('./div[3]//text()')
    price = "".join(price)
    fp.write(title + ':' + price + '
')    
fp.close()
print("over!")

# - 解析图片数据：http://pic.netbian.com/4kmeinv/
import requests
import urllib
import os
from lxml import etree

url = 'http://pic.netbian.com/4kmeinv/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36'
}
response = requests.get(url=url,headers=headers)
# response.encoding = 'utf-8'
page_text = response.text

tree = etree.HTML(page_text)

li_list = tree.xpath('//div[@class="slist"]/ul/li')

if not os.path.exists('./imgs'):
    os.mkdir('./imgs')

for li in li_list:
    title = li.xpath('./a/b/text()')[0]
    img_name = title.encode('iso-8859-1').decode('gbk')
    img_url = 'http://pic.netbian.com' + li.xpath('./a/img/@src')[0]
    img_path = './imgs/' + img_name + '.jpg'
    urllib.request.urlretrieve(url=img_url,filename=img_path)
    print(img_name,"下载成功")
print("over!!!")

#【重点】下载煎蛋网中的图片数据：http://jandan.net/ooxx
#数据加密  (反爬机制)
import requests
import urllib
import os
import base64
from lxml import etree

url = 'http://jandan.net/ooxx'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36'
}

page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)

if not os.path.exists('./jiandan'):
    os.mkdir('./jiandan')

img_hash_list = tree.xpath('//span[@class="img-hash"]/text()')
for img_hash in img_hash_list:
    img_url = 'http:' + base64.b64decode(img_hash).decode()
    img_name = img_url.split('/')[-1]
    img_path = './jiandan/' + img_name
    urllib.request.urlretrieve(url=img_url,filename=img_path)
print('over!')

#爬取站长素材中的简历模板
import requests
import random
import os
from lxml import etree


url = 'http://sc.chinaz.com/jianli/free_%s.html'

headers = {
    'Connection': 'close', # 当请求成功后，马上断开该次请求（及时释放请求池中的资源）
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36'
}

if not os.path.exists('./jianli'):
    os.mkdir('./jianli')

for i in range(1, 4):
    if i == 1:
        new_url = 'http://sc.chinaz.com/jianli/free.html'
    else:
        new_url = format(url % i)

    response = requests.get(url=new_url, headers=headers)
    response.encoding = 'utf8'
    page_text = response.text

    tree = etree.HTML(page_text)

    div_list = tree.xpath('//div[@id="container"]/div')
    for div in div_list:
        name = div.xpath('./p//text()')[0]
        detail_url = div.xpath('./a/@href')[0]

        detail_page_text = requests.get(url=detail_url, headers=headers).text
        tree = etree.HTML(detail_page_text)
        download_list = tree.xpath('//div[@class="clearfix mt20 downlist"]/ul/li/a/@href')
        download_url = random.choice(download_list)
        data = requests.get(url=download_url, headers=headers).content
        file_name = name + '.rar'
        file_path = './jianli/' + file_name

        with open(file_path,'wb') as fp:
            fp.write(data)
            print(file_name, "下载成功")
    
print('over!')

import requests
from lxml import etree


url = 'https://www.aqistudy.cn/historydata/'
headers = {
    'Connection': 'close', # 当请求成功后，马上断开该次请求（及时释放请求池中的资源）
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36'
}

page_text = requests.get(url=url, headers=headers).text
tree = etree.HTML(page_text)
div_list = tree.xpath('//div[@class="col-lg-9 col-md-8 col-sm-8 col-xs-12"]/div')
print(div_list)

for div in div_list:
    title = div.xpath('./div[1]//text()')[0]
    print(title)
    ul_list = div.xpath('./div[2]/ul | ./div[2]/ul')
    
    for ul in ul_list:
        fl = ul.xpath('./div[1]//text()')
        if fl:
            print(fl[0])
        li_list = ul.xpath('./li | ./div[2]/li')
        
        for li in li_list:
            city_name = li.xpath('./a/text()')[0]
            print(city_name)

图片懒加载：找对属性

代理ip的简单使用

#设置请求的代理ip: www.goubanjia.com  快代理  西祠代理
#代理ip的类型必须和请求url的协议头保持一致
import requests

url = 'https://www.baidu.com/s?wd=ip'

page_text = requests.get(url=url, headers=headers, proxies={'https': '114.88.53.19:53281'}).text

with open('./ip.html','w',encoding='utf-8') as fp:
    fp.write(page_text)