Python：爬虫百度贴吧图片

最新推荐文章于 2021-07-07 21:40:30 发布

hellolijunshy

最新推荐文章于 2021-07-07 21:40:30 发布

阅读量148

点赞数

分类专栏： Python操作总结

本文链接：https://blog.csdn.net/Hellolijunshy/article/details/90962664

版权

Python操作总结专栏收录该内容

17 篇文章 5 订阅

订阅专栏

#下载单个图片
import requests
def getHtml(url,headers):
    html=requests.get(url,headers=headers)
    return html.text

if __name__=="_main_":
    url = "http://tieba.baidu.com/p/6150967421"
    headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.80 Safari/537.36"
    } 

    html=getHtml(url,headers)
#print(html)
src='http://imgsrc.baidu.com/forum/w%3D580/sign=a6debc827c0e0cf3a0f74ef33a47f23d/2a66d0160924ab18a1a7f0a73bfae6cd7a890be8.jpg'

print(requests.get(src).content)
with open("1.jpg","wb") as f:
    f.write(requests.get(src).content)
    
    
    
#下载一页图片
import requests
from lxml import etree

def getHtml(url,headers):
    html=requests.get(url,headers=headers)
    return html.text
def getImagList(html):
    Selector=etree.HTML(html)
    imaglist=Selector.xpath('//img[@class="BDE_Image"]/@src')
    return imaglist


url = "http://tieba.baidu.com/p/6120663321"
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.80 Safari/537.36"
} 

html=getHtml(url,headers)
ImagList=getImagList(html)
print(ImagList)
len(ImagList)

for i,each in enumerate(ImagList):
    filename='{}.jpg'.format(i)
    with open(filename,"wb") as f:
         f.write(requests.get(each).content)