爬虫 xpath 获取方式

回顾 bs4

• 实例化bs对象,将页面源码数据加载到该对象中
• 定位标签:find('name',class_='xxx') findall() select()
• 将标签中的文本内容获取 string text get_text() a['href']

xpath

环境安装: pip install lxml

原理解析:

获取页面的源码数据

实例化etree对象,并将页面源码数据加载到该对象中

调用该对象xpath方法进行指定标签的定位

注意:xpath必须结合者xpath的表达式进行标签定位和内容捕获

/html/head/title
//head/title
//title

通过xpath进行获取数据

#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/?utm_source=market&spm=u-2d2yxv86y3v43nkddh1.BDPCPZ_BT&PGTID=0d30000c-0047-e4e6-f587-683307ca570e&ClickID=1'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 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='utf-8')
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+'\n')
fp.close()
print('over')

#调用xpath 返回的是一个列表结构,使用索引

利用xpath处理中文乱码

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

url = 'http://pic.netbian.com/4kmeinv/'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
response = requests.get(url=url,headers=headers)
#response.encoding = 'utf-8'
if not os.path.exists('./imgs'):
    os.mkdir('./imgs')
page_text = response.text

tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@class="slist"]/ul/li')
for li in li_list:
    img_name = li.xpath('./a/b/text()')[0]
    #处理中文乱码
    img_name = img_name.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_path,'下载成功!')
print('over!!!')

#通过encode('iso-8859-1').decode('gbk')编译
#或使用response.encoding = 'utf-8'

xpath在遇到加密base64时解决加密a标签

#【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
from lxml import etree
import base64
import urllib

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
url = 'http://jandan.net/ooxx'
page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
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]
    urllib.request.urlretrieve(url=img_url,filename=img_name)

xpath获取两次a标签进行获取及分页判断

#爬取站长素材中的简历模板
import requests
import random
from lxml import etree
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 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
url = 'http://sc.chinaz.com/jianli/free_%d.html'
for page in range(1,4):
    if page == 1:
        new_url = 'http://sc.chinaz.com/jianli/free.html'
    else:
        new_url = format(url%page)

    response = requests.get(url=new_url,headers=headers)
    response.encoding = 'utf-8'
    page_text = response.text

    tree = etree.HTML(page_text)
    div_list = tree.xpath('//div[@id="container"]/div')
    for div in div_list:
        detail_url = div.xpath('./a/@href')[0]
        name = div.xpath('./a/img/@alt')[0]

        detail_page = requests.get(url=detail_url,headers=headers).text
        tree = etree.HTML(detail_page)
        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
        fileName = name+'.rar'
        with open(fileName,'wb') as fp:
            fp.write(data)
            print(fileName,'下载成功')

            //*[@id="down"]/div[2]/ul/li[6]/a

xpath 利用 |  实现并集获取数据

#解析所有的城市名称
import requests
from lxml import etree
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 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
url = 'https://www.aqistudy.cn/historydata/'
page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@class="bottom"]/ul/li |  //div[@class="bottom"]/ul/div[2]/li')
for li in li_list:
    city_name = li.xpath('./a/text()')[0]
    print(city_name)

proxies 代理设置

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

page_text = requests.get(url=url,headers=headers,proxies={'https':'61.7.170.240:8080'}).text

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

防卫机制:
robots

UA

数据加密

懒加载

代理ip