python——爬取网页图片

BeautifulSoup    https://www.crummy.com/software/BeautifulSoup/bs4/doc/index.zh.html#id10

步骤：

1. 发送http请求，获取html
2. 获取所有img标签
3. 用正则表达式取出src的网址
4. 返回图片网址的html，用二进制保存为图片

代码： 

import urllib.request
from bs4 import BeautifulSoup
import re

picture_url = "http://www.umei.cc/"

def get_html(url):
    res = urllib.request.urlopen(url)
    html = res.read()
    return html

def parse_html(htmlfile):
    mysoup = BeautifulSoup(htmlfile,'html.parser')
    picture_src = mysoup.findAll('img')
    imgre = re.compile(r'src="(.*?)"')
    for i in range(len(picture_src)):
        s = str(picture_src[i])
        img_url = re.findall(imgre,s)
        if img_url:
            img_url = img_url[0]
            with open("G:/python/picture/%s.jpg"%(i+1),'wb') as f:
                try:
                    res = urllib.request.urlopen(img_url)
                    html = res.read()
                    f.write(html)
                except (urllib.error.URLError,ValueError) as e:
                    print("urllib.error.URLError:",e)

parse_html(get_html(picture_url))

效果：

用requests爬取，并用tkinter做一个简单界面 

效果图：

输入网址，点击下载： 

下载完成： 

代码：

import requests
from bs4 import BeautifulSoup
import os
import tkinter as tk
from tkinter import scrolledtext
from tkinter.messagebox import *
def download():
    url = src.get("0.0","end")
    url = url.lstrip()
    url = url.rstrip()
    if len(url) == 0:
        return -1
    html = get_html(url)
    src.delete("0.0","end")
    parser_data(html)

def get_html(url):
    if not url[:7] == "http://":
        url = "http://" + url
    head = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.75 Safari/537.36"}
    res = requests.get(url,headers=head)
    return res.content

def parser_data(html):
    soup = BeautifulSoup(html,"html.parser")
    img = soup.find_all("img") #获取所有的img标签
    size = len(img)
    print(size)
    try:
        os.mkdir("download")
    finally:
        # 获取当前文件夹的文件数目，编号从之后开始，以免覆盖之前的图片
        count = len(os.listdir("download"))
        i = count
        for x in img:
            i += 1
            url = x["src"]#获取src属性中的网址
            print(url)
            image = get_html(url)
            with open("./download/%s.jpg"%i,"wb") as f:
                f.write(image)
        showinfo(title="提示",message="下载完成！")

mainWindow = tk.Tk()
mainWindow.minsize(650,30)
mainWindow.maxsize(650,30)
mainWindow.title("图片下载器")
font_text = "Calibri"
font_size = 15
src = tk.Text(mainWindow,font=(font_text,font_size))
src.place(x=50,y=0,width=600,height=30)
down = tk.Button(mainWindow,font=(font_text,font_size),text="下载",
                        bg="#2ECCFA",fg="white",command=lambda:download())
down.place(x=0,y=0,width=50,height=30)
mainWindow.mainloop()