python - 如何解决此错误：TypeError：'NoneType'对象没有属性'__getitem__'(How to resolve this error: TypeError: 'NoneType' object has no attribute '__getitem__')

Question

I was trying to download a full course from LinkedIn Learning using a code from GitHub.

(我试图使用GitHub上的代码从LinkedIn Learning下载完整的课程。)

I have already downloaded a couple of courses before but this time, when I tried to download another course, the error appeared.

(我之前已经下载了几门课程，但是这次，当我尝试下载另一门课程时，出现了错误。)

PS: I do have a premium LinkedIn membership.

(PS：我确实有高级LinkedIn会员。)

Can't watch a course online all the time - that's why I download on my PC.

(无法一直在线观看课程-这就是为什么我要在PC上下载的原因。)

# -*- coding: utf-8 -*-
import requests
from requests import Session
from bs4 import BeautifulSoup
import urllib
import sys
import re
import os
import string
import config
import logging

reload(sys)
sys.setdefaultencoding('utf-8')

login_url = 'https://www.linkedin.com/'
post_login_url = 'https://www.linkedin.com/uas/login-submit'
course_api_url = 'https://www.linkedin.com/learning-api/detailedCourses??fields=fullCourseUnlocked,releasedOn,' 
          'exerciseFileUrls,exerciseFiles&addParagraphsToTranscript=true&courseSlug=%s&q=slugs'
video_api_url = 'https://www.linkedin.com/learning-api/detailedCourses?addParagraphsToTranscript=false&courseSlug=%s' 
            '&q=slugs&resolution=_720&videoSlug=%s'
headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'en-US,en;q=0.9',
    'Connection': 'keep-alive',
    'Content-Type': 'application/x-www-form-urlencoded',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                  'Chrome/66.0.3359.181 Safari/537.36'
}

logging.basicConfig(format='%(asctime)s - %(levelname)s - %(message)s', level=logging.INFO)

class Lld:
    def __init__(self):
        self.session = Session()
        self.base_path = config.BASE_DOWNLOAD_PATH if config.BASE_DOWNLOAD_PATH else 'out'

    @staticmethod
    def plain_cookies(cookies):
        plain = ''
        for k, v in cookies.iteritems():
            plain += k + '=' + v + '; '
        return plain[:-2]

    @staticmethod
    def format_string(raw_string):
        replacement_dict = {u'?': 'Ae', u'?': 'Oe', u'ü': 'Ue', u'?': 'ae', u'?': 'oe', u'ü': 'ue', ':': ' -'}
        invalid_chars = r'[^A-Za-z0-9-.]+'
        u_map = {ord(key): unicode(val) for key, val in replacement_dict.items()}
        raw_string = raw_string.translate(u_map)
        raw_string = re.sub(invalid_chars, ' ', raw_string).strip().encode('utf-8')
        i = 0
        for c in raw_string:
            if c in string.ascii_letters:
                break
            i += 1
        return raw_string[i:]

    @staticmethod
    def format_time(ms):
        seconds, milliseconds = divmod(ms, 1000)
        minitues, seconds = divmod(seconds, 60)
        hours, minitues = divmod(minitues, 60)
        return '%d:%02d:%02d,%02d' % (hours, minitues, seconds, milliseconds)

    def download_file(self, url, path, file_name):
        resp = self.session.get(url, stream=True)
        if not os.path.exists(path):
            os.makedirs(path)
        try:
            with open(path + '/' + file_name, 'wb') as f:
                for chunk in resp.iter_content(chunk_size=1024):
                    if chunk:
                        f.write(chunk)
        except Exception as e:
            os.remove(path + '/' + file_name)
            print(e)

    def download_sub(self, subs, path, file_name):
        with open(path + '/' + file_name, 'a') as f:
            i = 1
            for sub in subs:
                t_start = sub['transcriptStartAt']
                if i == len(subs):
                    t_end = t_start + 5000
                else:
                    t_end = subs[i]['transcriptStartAt']
                caption = sub['caption']
                f.write('%s
' % str(i))
                f.write('%s --> %s
' % (self.format_time(t_start), self.format_time(t_end)))
                f.write('%s

' % caption)
                i += 1

    def download_desc(self, desc, course_url, path, file_name):
        if not os.path.exists(path):
            os.makedirs(path)
        with open(path + '/' + file_name, 'a') as f:
            f.write('%s

%s' % (desc, course_url))

    def get_logged_session(self):
        logging.info('Authenticating to LinkedIn')
        login_page = BeautifulSoup(self.session.get(login_url).text, 'html.parser')
        csrf = login_page.find(id='loginCsrfParam-login')['value']
        logging.info('Csfr token: %s' % csrf)
        login_data = urllib.urlencode(
            {'session_key': config.USERNAME, 'session_password': config.PASSWORD, 'isJsEnabled': 'false',
             'loginCsrfParam': csrf})
        headers['Cookie'] = self.plain_cookies(requests.utils.dict_from_cookiejar(self.session.cookies))
        self.session.headers.update(headers)
        resp = self.session.post(post_login_url, data=login_data, allow_redirects=True)
        if resp.status_code != 200:
            logging.error('Could not authenticate to LinkedIn')
        else:
            logging.info('Authentication successfully completed')

    def download_courses(self):
        token = self.session.cookies.get('JSESSIONID').replace('"', '')
        self.session.headers['Csrf-Token'] = token
        self.session.headers['Cookie'] = self.plain_cookies(requests.utils.dict_from_cookiejar(self.session.cookies))
        self.session.headers.pop('Accept')

        for course in config.COURSES:
            resp = self.session.get(course_api_url % course)
            course_data = resp.json()['elements'][0]
            course_name = self.format_string(course_data['title'])
            logging.info('Starting download of course [%s]...' % course_name)
            course_path = '%s/%s' % (self.base_path, course_name)
            chapters_list = course_data['chapters']
            chapter_index = 1
            logging.info('Parsing course's chapters...')
            logging.info('%d chapters found' % len(chapters_list))
            for chapter in chapters_list:
                chapter_name = self.format_string(chapter['title'])
                logging.info('Starting download of chapter [%s]...' % chapter_name)
                chapter_path = '%s/%s - %s' % (course_path, str(chapter_index).zfill(2), chapter_name)
                if chapter_name == '':
                    chapter_path = chapter_path[:-3]
                videos_list = chapter['videos']
                video_index = 1
                logging.info('Parsing chapters's videos')
                logging.info('%d videos found' % len(videos_list))
                for video in videos_list:
                    video_name = self.format_string(video['title'])
                    video_slug = video['slug']
                    video_data = (self.session.get(video_api_url % (course, video_slug)))
                    try:
                        video_url = re.search('"progressiveUrl":"(.+)","streamingUrl"', video_data.text).group(1)
                    except:
                        logging.error('Can't download the video [%s], probably is only for premium users' % video_name)
                        continue
                    logging.info('Downloading video [%s]' % video_name)
                    self.download_file(video_url, chapter_path, '%s - %s.mp4' % (str(video_index).zfill(2), video_name))
                    video_data = video_data.json()['elements'][0]
                    if config.SUBS:
                        try:
                            subs = video_data['selectedVideo']['transcript']['lines']
                        except KeyError:
                            logging.info('No subtitles avaible')
                        else:
                            logging.info('Downloading subtitles')
                            self.download_sub(subs, chapter_path, '%s - %s.srt' % (str(video_index).zfill(2), video_name))
                    video_index += 1
                chapter_index += 1

            exercises_list = course_data['exerciseFiles']
            for exercise in exercises_list:
                try:
                    ex_name = exercise['name']
                    ex_url = exercise['url']
                except (KeyError, IndexError):
                    logging.info('Can't download an exercise file for course [%s]' % course_name)
                else:
                     self.download_file(ex_url, course_path, ex_name)
            description = course_data['description']
            logging.info('Downloading course description')
            self.download_desc(description, 'https://www.linkedin.com/learning/%s' % course, course_path, 'Description.txt')


def main():
    lld = Lld()
    lld.get_logged_session()
    lld.download_courses()


if __name__ == '__main__':
    main()

Error that appears

(出现的错误)

Traceback (most recent call last):
  File "lld.py", line 187, in <module>
    main()
  File "lld.py", line 182, in main
    lld.get_logged_session()
  File "lld.py", line 104, in get_logged_session
    csrf = login_page.find(id='loginCsrfParam-login')['value']
TypeError: 'NoneType' object has no attribute '__getitem__'

  ask by Jay translate from so

Answer 1

This error means that login_page.find(id='loginCsrfParam-login')['value'] has a null value (a value of None).

(此错误意味着login_page.find(id='loginCsrfParam-login')['value']具有空值（值为None）。)

This is probably because the file you are parsing with Beautiful Soup (a very slow parser btw, but good for learning) does not contain the requested tag, or that tag does not have the 'value' attribute

(这可能是因为您正在使用Beautiful Soup解析的文件（一个非常慢的解析器，但很容易学习）不包含请求的标记，或者该标记没有'value'属性)

EDIT:

(编辑：)
The reason you are getting this error is that there is no tag with the id "loginCsrfParam-login"

(您收到此错误的原因是，没有ID为“ loginCsrfParam-login”的标签)

Here is a Diagram of Whats going on in the interpreter:

(这是解释器中发生的事情的图表：)

1. Page is fetched (www.linkedin.com/index.html), this page does not contain anything with the id of "loginCsrfParam-login".

   (页面已获取（www.linkedin.com/index.html），此页面不包含ID为“ loginCsrfParam-login”的任何内容。)

2. BeautifulSoup parses the page for a tag with the "loginCsrfParam-login", it doesn't find it, so it returns None.

   (BeautifulSoup会使用“ loginCsrfParam-login”解析页面中的标签，但找不到该标签，因此它返回None。)

3. You didn't try to write safe code, so you didn't check the return value of parse.

   (您没有尝试编写安全的代码，因此也没有检查parse的返回值。)

4. Python failed because you tried to refer to the member of an empty class

   (Python失败，因为您尝试引用空类的成员)