案例-爬取爱斗图图片：xpath

网址： https://aidotu.com/search/0-0-0-1.html

 

xpath代码：

import requests
import json
from lxml import etree
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
url  = 'https://aidotu.com/search/0-0-0-1.html'

def down_img(file_name,url):
    img_resp = requests.get(url, headers = headers)
    with open(file_name, mode="wb") as f:
        f.write(img_resp.content)

def get_info(url):
    resp = requests.get(url, headers=headers)
    resp.encoding = 'UTF-8'
    html_tree = etree.HTML(resp.text)
    data = html_tree.xpath('//div[@class="main"]/div/div/div[1]/div[2]/div/div')
    for item in data:
        item_name = item.xpath('./a/@title')[0]
        img_url = item.xpath('./a/img/@src')[0]
        full_url = "https:{}".format(img_url)
        url_suffix = full_url.split('.')[-1]
        file_name = '{}.{}'.format(item_name, url_suffix)
        #print("名字==>", file_name)
        #print("img_url==>", full_url)
        down_img(file_name,full_url)

# 分页
for item in range(1,224):
    full_url = "https://aidotu.com/search/0-0-0-{}.html".format(item)
    get_info(full_url)