[已解决]关于爬虫爬取jandan图片出错,求高手指点

ONtHE

        import urllib.request
import os
import random


def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.65 Safari/537.36')

    response = urllib.request.urlopen(req)
    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[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):

@小甲鱼
        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()
这是源码跟着视频写的,在python3.6中会报错,求高手指点迷津

最佳答案

月排行榜 / 总排行榜

gopythoner

2017-11-12 19:09:12

图片前面加上http:

跳转到最佳答案楼层

gopythoner

图片前面加上http:

ONtHE

gopythoner 发表于 2017-11-12 19:09
图片前面加上http:

脑子里一直想,刚出去一趟,能知道在哪加了,谢谢