初学爬虫-veer图片下载

导包

import requests
import pandas as pd
from lxml import etree

目标网站

target='https://www.veer.com/photo/'

请求头

headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36'
        }

获取响应

html = requests.get(target,headers=headers)

xpath解析

req = etree.HTML(html.text)
src = req.xpath('//div[@class="site_width"]/section/div/article/a/figure/img/@src')
name = req.xpath('//div[@class="site_width"]/section/div/article/a/figure/figcaption/text()')

通过pandas获取图片的真实地址

data = pd.DataFrame()
data['src'] = src
data['src'] = 'http:'+data['src'].astype('str')
data['name'] = name

写入本地文件

def save(name, content):
    with open('images/'+str(name) + '.jpg', 'wb')as f:
        f.write(content)

遍历图片地址，下载

if __name__ == '__main__':
    for dat,name in zip(data['src'],data['name']):
        print(dat)
        re = requests.get(dat).content
        save(name,re)

完整代码

import requests
import pandas as pd
from lxml import etree

target='https://www.veer.com/photo/'

headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36'
        }
html = requests.get(target,headers=headers)
# print(html.text)
req = etree.HTML(html.text)
src = req.xpath('//div[@class="site_width"]/section/div/article/a/figure/img/@src')
name = req.xpath('//div[@class="site_width"]/section/div/article/a/figure/figcaption/text()')
data = pd.DataFrame()
data['src'] = src
data['src'] = 'http:'+data['src'].astype('str')
data['name'] = name

def save(name, content):
    with open('images/'+str(name) + '.jpg', 'wb')as f:
        f.write(content)
if __name__ == '__main__':
    for dat,name in zip(data['src'],data['name']):
        print(dat)
        re = requests.get(dat).content
        save(name,re)