关于煎蛋爬虫

qzgy43210

程序完成后先跳出



附上代码


import urllib.request
import os


def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 BIDUBrowser/8.4 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('html'+html[a+9:b+4])
         else:
             b = a + 9
         a = html.find('img src=',b)
    for each in img_addrs:
        print(each)
    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 ='XXXX',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()

醉梦醒

find_imgs(url)函数那里是http不是html，看这里http://bbs.fishc.com/forum.php?m ... p;page=1#pid2872850

ooxx7788

1.   img_addrs.append('html'+html[a+9:b+4])

复制代码

改成

1.   img_addrs.append('http:'+html[a+9:b+4])

复制代码