urllib.error.HTTPError: HTTP Error 403: Forbidden

flybeyondsky

import urllib.request
import os

def get_page(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.101 Safari/537.36')
    response = urllib.request.urlopen(url)
    html=response.read().decode('utf-8')

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

    print(html[a:b])


def find_imgs(url):
    pass

def save_imgs(folder,img_addrs):
    pass

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()

按照小甲鱼的一步一步来，找打印页面的时候 总是报错，urllib.error.HTTPError: HTTP Error 403: Forbidden！应该如何解决？

flybeyondsky

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 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.101 Safari/537.36')


    proxies = ['163.177.79.5:80','124.65.163.10:8080','218.61.39.54:55366']
    proxy = random.choice(proxies)
    
    proxy_support = urllib.request.ProxyHandler({'http':proxy})
    opener = urllib.request.build_opener(proxy_support)
    urllib.request.install_opener(opener)
    
    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') + len('current-comment-page')+3
    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.wirte(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()

加入了代理也不可以哦~~~~

flybeyondsky

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 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 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') + len('current-comment-page')+3
    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)

    for each in img_addrs:
        print(each)


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.wirte(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'
        print(page_url)
        img_addrs = find_imgs(page_url)
        save_imgs(folder,img_addrs)

if __name__ == '__main__':
    download_mm()

出现这样的错误：

http://jandan.net/ooxx/page-1471#comments
http://ww4.sinaimg.cn/mw600/006a7OZUgw1euanawdpncj30dw0dwdh6.jpg
http://ww4.sinaimg.cn/mw600/006a7OZUgw1euanaxrhwfj30dw0dw0u3.jpg
http://ww3.sinaimg.cn/mw600/006a7OZUgw1euanaze0r0j30dw0dw3zw.jpg
http://ww2.sinaimg.cn/mw600/0069EIYdgw1euacgpu1emj30go0m7n06.jpg
http://ww1.sinaimg.cn/mw600/0069EIYdgw1euacgre6sqj30go0m7tat.jpg
http://ww1.sinaimg.cn/mw600/0069EIYdgw1euacguk9ajj30go0m742w.jpg
http://ww4.sinaimg.cn/mw600/0069EIYdgw1euacgwx0x7j30go0m7n1r.jpg
http://ww2.sinaimg.cn/mw600/0069EIYdgw1euacgmiwcvj30go0p2tct.jpg
http://ww1.sinaimg.cn/mw600/8d07dee3tw1eopg9km062j20xc1b4dp7.jpg
http://ww2.sinaimg.cn/mw600/8d07dee3tw1eopg9mm50nj20gm0b7myb.jpg
http://ww1.sinaimg.cn/mw600/df43c939jw1euaixwqnktj20zk1eawqc.jpg
http://ww2.sinaimg.cn/mw600/df43c939jw1euabuk0grnj20f00mita6.jpg
"http://s.jandan.com/static/gggg/56fanli4/"+a+"\" width=\"125\" height=\"125\" border=\"0\" /></a>");

</script><!-- 56fanli -->

                                <script>

var str=new Array("1.jpg
"http://s.jandan.com/static/gggg/niuza/"+a+"\" width=\"125\" height=\"125\" border=\"0\" /></a>");

</script><!-- niuza -->

                                <script>

var str=new Array("1.jpg
Traceback (most recent call last):
  File "C:\Documents and Settings\Administrator\桌面\download_mm.py", line 65, in <module>
    download_mm()
  File "C:\Documents and Settings\Administrator\桌面\download_mm.py", line 62, in download_mm
    save_imgs(folder,img_addrs)
  File "C:\Documents and Settings\Administrator\桌面\download_mm.py", line 43, in save_imgs
    for each in img_addrs:
TypeError: 'NoneType' object is not iterable

@小甲鱼@

tongyangdecuowu,buzhdiaowruhejiejue

longwutian004

听说是被禁止爬虫？

杀手carry

报错是这个     for each in img_addrs:
TypeError: 'NoneType' object is not iterable

请问怎么解决？

杀手carry

是如果列表为None 导致的TypeError: 'NoneType' object is not iterable么

hrbhongwei

urllib.error.HTTPError: HTTP Error 403: Forbidden 加入代理了 还是不可以 这个问题怎么解决呢

wu1996

同样的问题  很无奈

人品弟弟

还是不行，求教/

zrovsion

不知道楼主解决了没