[已解决]哪位行行好帮我看看我该怎么办

CD84380973

import urllib.request
import os

def url_open(url):
    req = urllib.requests.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 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_img(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('https:'+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'
        find_addrs = find_imgs(page_url)
        save_imgs(img_addrs)

if __name__ == "__main__":
    download_mm()


Traceback (most recent call last):
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 60, in <module>
    download_mm()
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 51, in download_mm
    page_num = int(get_page[url])
TypeError: 'function' object is not subscriptable

最佳答案

月排行榜 / 总排行榜

十月故里

2020-4-1 21:12:04

CD84380973 发表于 2020-4-1 21:01
越整越负了，我错了那么多行？

不是这么说的，看最后一行的就行，它类似牵一发动全身，由于一个地方错误引起的一连串程序运行错误而已，但关键就是看返回信息的最后一句说的啥，调用的库除开，就看你代码块部分的错误的最后一行，我给你捋捋
Traceback (most recent call last):
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 60, in <module>
    download_mm()
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 51, in download_mm
    page_num = int(get_page(url))
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 13, in get_page
    html = url_open(url).decode(utf-8)
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 7, in url_open
    response = urllib.request.urlopen(url)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 222, in urlopen
    return opener.open(url, data, timeout)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 531, in open
    response = meth(req, response)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 640, in http_response
    response = self.parent.error(
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 569, in error
    return self._call_chain(*args)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 502, in _call_chain
    result = func(*args)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 649, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 403: Forbidden
这是你的反错信息（两行为一组，第一行告诉你错误的地方在第几行，第二行告诉你错误的是代码具体是什么）
你看第一段说在执行 download_mm()的时候引起的错误，而这个错误的地方在哪里
这时候看第二段  page_num = int(get_page(url))，同样这里引起的错误在哪里，依次类推
到属于你代码的最后一部分就是错误的根源response = urllib.request.urlopen(url)
然后后面的部分属于引用库里面的函数调用，直接看最后一行
HTTP Error 403: Forbidden，就是说你在用urllib.request.urlopen(url)，打开这个链接的时候，由于对面不应答或者url本来是错的，导致你的代码运行出错

跳转到最佳答案楼层

zltzlt

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; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 '
                   '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_img(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('https:' + 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'
        find_addrs = find_img(page_url)
        save_imgs(folder, find_addrs)


if __name__ == "__main__":
    download_mm()

BngThea

把中括号改成小括号

CD84380973

BngThea 发表于 2020-4-1 20:18
把中括号改成小括号

大神说的是什么位置的中括号？

CD84380973

zltzlt 发表于 2020-4-1 20:18

我把您的代码复制进去了还是报的TypeError: 'function' object is not subscriptable

十月故里

TypeError: 'function' object is not subscriptable
返回信息告诉你函数对象不能用下标索引
回到你错误的行可以看到
page_num = int(get_page[url])
get_page【url】这里你用的是中括号【】，表示索引呢
改成小括号

CD84380973

十月故里 发表于 2020-4-1 20:38
TypeError: 'function' object is not subscriptable
返回信息告诉你函数对象不能用下标索引
回到你错误 ...

听您改了，然后报了这个错  module 'urllib' has no attribute 'requests'

Hoiste

CD84380973 发表于 2020-4-1 20:43
听您改了，然后报了这个错  module 'urllib' has no attribute 'requests'

request多打了个s

CD84380973

十月故里 发表于 2020-4-1 20:38
TypeError: 'function' object is not subscriptable
返回信息告诉你函数对象不能用下标索引
回到你错误 ...

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; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 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_img(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('https:'+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'
        find_addrs = find_imgs(page_url)
        save_imgs(img_addrs)

if __name__ == "__main__":
    download_mm()


您说的地方我改了，第六行request多打了s也去了，结果还是报TypeError: 'function' object is not subscriptable  您帮我看看还有哪里用错了中括号呢

CD84380973

Hoiste 发表于 2020-4-1 20:49
request多打了个s

这两处改了还是报的TypeError: 'function' object is not subscriptable，难道还有哪里中括号用错了？

十月故里

你把全部返回信息贴上来

CD84380973

十月故里 发表于 2020-4-1 20:50
你把全部返回信息贴上来

Traceback (most recent call last):
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 60, in <module>
    download_mm()
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 51, in download_mm
    page_num = int(get_page(url))
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 13, in get_page
    html = url_open(url).decode(utf-8)
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 7, in url_open
    response = urllib.request.urlopen[url]
TypeError: 'function' object is not subscriptable

十月故里

我看你第一个def url_open这里就有一个写错的[]

Hoiste

CD84380973 发表于 2020-4-1 20:50
这两处改了还是报的TypeError: 'function' object is not subscriptable，难道还有哪里中括号用错了？

发下完整错误信息吧，错误说明是用下标去访问不可以下标访问的对象了

CD84380973

十月故里 发表于 2020-4-1 20:52
我看你第一个def url_open这里就有一个写错的[]

我把那处改了，现在是

Traceback (most recent call last):
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 60, in <module>
    download_mm()
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 51, in download_mm
    page_num = int(get_page(url))
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 13, in get_page
    html = url_open(url).decode(utf-8)
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 7, in url_open
    response = urllib.request.urlopen(url)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 222, in urlopen
    return opener.open(url, data, timeout)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 531, in open
    response = meth(req, response)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 640, in http_response
    response = self.parent.error(
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 569, in error
    return self._call_chain(*args)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 502, in _call_chain
    result = func(*args)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 649, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 403: Forbidden

BngThea

CD84380973 发表于 2020-4-1 20:36
大神说的是什么位置的中括号？

函数调用啊
你download_mm 中调用了get_page

十月故里

CD84380973 发表于 2020-4-1 20:52
Traceback (most recent call last):
  File "C:%users\39436\Desktop\python练习\download_mm.py", lin ...

果然，你平时报错的时候可以看报错信息，error上面一行就是你最后报错的地方，然后根据报错信息来改正就好了，这里的问题还是错误的写成[]了，调用函数用的是()，索引之类才用[]

CD84380973

Hoiste 发表于 2020-4-1 20:54
发下完整错误信息吧，错误说明是用下标去访问不可以下标访问的对象了

现在改了是这样了
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; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 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_img(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('https:'+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'
        find_addrs = find_imgs(page_url)
        save_imgs(img_addrs)

if __name__ == "__main__":
    download_mm()



Traceback (most recent call last):
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 60, in <module>
    download_mm()
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 51, in download_mm
    page_num = int(get_page(url))
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 13, in get_page
    html = url_open(url).decode(utf-8)
  File "C:\Users\39436\Desktop\python练习\download_mm.py", line 7, in url_open
    response = urllib.request.urlopen(url)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 222, in urlopen
    return opener.open(url, data, timeout)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 531, in open
    response = meth(req, response)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 640, in http_response
    response = self.parent.error(
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 569, in error
    return self._call_chain(*args)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 502, in _call_chain
    result = func(*args)
  File "C:\Users\39436\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 649, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 403: Forbidden

十月故里

CD84380973 发表于 2020-4-1 20:55
我把那处改了，现在是

Traceback (most recent call last):

现在是403了，你的url要么有问题，要么对面禁止你访问了，你先用你自己浏览器打开下你的url看能不能正常打开，你这里应该是小甲鱼的网址，我记得好像网址变了

CD84380973

十月故里 发表于 2020-4-1 20:56
果然，你平时报错的时候可以看报错信息，error上面一行就是你最后报错的地方，然后根据报错信息来改正就 ...

越整越负了，我错了那么多行？