数据爬取(图片，信息)

爬取网站上的图片：

import urllib.request
from bs4 import BeautifulSoup
import requests
import os
url='https://tieba.baidu.com/p/4893688124'
html=urllib.request.urlopen(url).read()
soup=BeautifulSoup(html,'html.parser')
jpg_data=soup.find_all('img',class_='BDE_Image')
print('jpg_data',jpg_data)
for i in jpg_data:
    data=i['src']
    name=i['size']
    r2=requests.get(data)
    #对图像网站发起请求
    fpath=os.path.join(r'C:\Users\abc\Desktop\python',name)
    with open(fpath+'.jpg','wb+')as f:
        f.write(r2.content)
print('保存成功')

---

爬取网站：

import urllib.request
from bs4 import BeautifulSoup
f=open(r'D:\anaconda\python程序\数据爬虫\padding.txt','a+',encoding='utf-8')
url="https://www.zhihu.com/question/19649693"
html=urllib.request.urlopen(url).read()
#读取网站数据
soup=BeautifulSoup(html,"lxml")
#将网页数据荣纳入soup中
#print(soup.prettify())
#打印格式
all=soup.find_all(class_='RichText ztext CopyrightRichText-richText')
#limit表示限制输出的条件
ALL=str(all).split('</div>')
#将所有恢复的内容妆花为字符型，并分隔开
for each in ALL:
    f.write(each+'\n')
f.close()