爬虫程序，从图片网站或者贴吧爬取图片（含代码）

github地址：https://github.com/531126085/Web-spider
download——mm是从煎蛋网上批量下载图片到自己新建的一个xxoo的文件夹下

import urllib.request
import os

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36')
    response = urllib.request.urlopen(url)
    html = response.read()
    return html

def get_page(url):
    html = url_open(url).decode('utf-8')

    a = html.find('current-comment-page') + 23
    b = html.find(']',a)

    return html[a:b]
 

def find_imgs(url):
    html = url_open(url).decode('utf-8') 
    img_addrs = []

    a = html.find('img src=')
    while a!=-1:
        b = html.find('.jpg',a, a+255)

        if b != -1:
            img_addrs.append('http:'+html[a+9:b+4])
        else:
            b = a+9
        a = html.find('img src=',b)
    return img_addrs
    
def save_imgs(folder,img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(filename,'wb') as f:
            img = url_open(each)
            f.write(img)

def download_mm(folder='ooxx',pages=10):
    os.mkdir(folder)
    os.chdir(folder)

    url = "http://jandan.net/ooxx/"
    page_num =int(get_page(url))
    for i in range(pages):
        page_num -= i
        page_url = url + 'page-' + str(page_num) + '#comments'
        img_addrs = find_imgs(page_url)
        save_imgs(folder,img_addrs)


if __name__=='__main__':
    download_mm()

download——quanyou是从权力的游戏贴吧上下载图片到当前的工作目录

import urllib.request
import re

def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')

    return html

def get_img(html):
    p = r'<img class="BDE_Image" src="([^"]+\.jpg)"'#采用正则表达式查找图片的地址
    imglist = re.findall(p,html)          #findall函数，如果正则表达式里有带（）的，则查找到之后会将括号的里面的信息返回给imglist
    
    for each in imglist:
        print(each)
    
    for each in imglist:
        filename = each.split("/")[-1]
        urllib.request.urlretrieve(each,filename,None)
        

if __name__=='__main__':
    url = "http://tieba.baidu.com/p/6093575289?pid=125013245611&cid=0#125013245611"
    get_img(open_url(url))