'''登錄'''
def login(self, username, password):
    lg = login.Login()
    infos_return, session = lg.icourse163(username, password)
    return infos_return, session

接著，我們簡(jiǎn)單講解一下如何下載對(duì)應(yīng)課程里的資料。首先，我們需要獲得課程相關(guān)的基本資料，隨便點(diǎn)開(kāi)個(gè)課程主頁(yè)就可以發(fā)現(xiàn)直接在返回的頁(yè)面里就有：

提取我們需要的課程信息的代碼實(shí)現(xiàn)如下：

# 從課程主頁(yè)面獲取信息
url = url.replace('learn/', 'course/')
response = self.session.get(url)
term_id = re.findall(r'termId : "(\d+)"', response.text)[0]
course_name = ' - '.join(re.findall(r'name:"(.+)"', response.text))
course_name = self.filterBadCharacter(course_name)
course_id = re.findall(r'https?://www.icourse163.org/(course|learn)/\w+-(\d+)', url)[0]
print(f'從課程主頁(yè)面獲取的信息如下:\n\t[課程名]: {course_name}, [課程ID]: {course_name}, [TID]: {term_id}')

接著利用這些信息來(lái)爬取對(duì)應(yīng)的資源列表：

# 獲取資源列表
resource_list = []
data = {
    'tid': term_id,
    'mob-token': self.infos_return['results']['mob-token'],
}
response = self.session.post('https://www.icourse163.org/mob/course/courseLearn/v1', data=data)
course_info = response.json()
file_types = [1, 3, 4]
for chapter_num, chapter in enumerate(course_info.get('results', {}).get('termDto', {}).get('chapters', [])):
    for lesson_num, lesson in enumerate(chapter.get('lessons', [])) if chapter.get('lessons') is not None else []:
        for unit_num, unit in enumerate(lesson.get('units', [])):
            if unit['contentType'] not in file_types: continue
            savedir = course_name
            self.checkdir(savedir)
            for item in [self.filterBadCharacter(chapter['name']), self.filterBadCharacter(lesson['name']), self.filterBadCharacter(unit['name'])]:
                savedir = os.path.join(savedir, item)
                self.checkdir(savedir)
            if unit['contentType'] == file_types[0]:
                savename = self.filterBadCharacter(unit['name']) + '.mp4'
                resource_list.append({
                    'savedir': savedir,
                    'savename': savename,
                    'type': 'video',
                    'contentId': unit['contentId'],
                    'id': unit['id'],
                })
            elif unit['contentType'] == file_types[1]:
                savename = self.filterBadCharacter(unit['name']) + '.pdf'
                resource_list.append({
                    'savedir': savedir,
                    'savename': savename,
                    'type': 'pdf',
                    'contentId': unit['contentId'],
                    'id': unit['id'],
                })
            elif unit['contentType'] == file_types[2]:
                if unit.get('jsonContent'):
                    json_content = eval(unit['jsonContent'])
                    savename = self.filterBadCharacter(json_content['fileName'])
                    resource_list.append({
                        'savedir': savedir,
                        'savename': savename,
                        'type': 'rich_text',
                        'jsonContent': json_content,
                    })
print(f'成功獲得資源列表, 數(shù)量為{len(resource_list)}')

最后根據(jù)資源類型解析下載即可：

# 下載對(duì)應(yīng)資源
pbar = tqdm(resource_list)
for resource in pbar:
    pbar.set_description(f'downloading {resource["savename"]}')
    # --下載視頻
    if resource['type'] == 'video':
        data = {
            'bizType': '1',
            'mob-token': self.infos_return['results']['mob-token'],
            'bizId': resource['id'],
            'contentType': '1',
        }
        while True:
            response = self.session.post('https://www.icourse163.org/mob/j/v1/mobileResourceRpcBean.getResourceToken.rpc', data=data)
            if response.json()['results'] is not None: break
            time.sleep(0.5 + random.random())
        signature = response.json()['results']['videoSignDto']['signature']
        data = {
            'enVersion': '1',
            'clientType': '2',
            'mob-token': self.infos_return['results']['mob-token'],
            'signature': signature,
            'videoId': resource['contentId'],
        }
        response = self.session.post('https://vod.study.163.com/mob/api/v1/vod/videoByNative', data=data)
        # ----下載視頻
        videos = response.json()['results']['videoInfo']['videos']
        resolutions, video_url = [3, 2, 1], None
        for resolution in resolutions:
            for video in videos:
                if video['quality'] == resolution:
                    video_url = video["videoUrl"]
                    break
            if video_url is not None: break
        if '.m3u8' in video_url:
            self.m3u8download({
                'download_url': video_url,
                'savedir': resource['savedir'],
                'savename': resource['savename'],
            })
        else:
            self.defaultdownload({
                'download_url': video_url,
                'savedir': resource['savedir'],
                'savename': resource['savename'],
            })
        # ----下載字幕
        srt_info = response.json()['results']['videoInfo']['srtCaptions']
        if srt_info:
            for srt_item in srt_info:
                srt_name = os.path.splitext(resource['savename'])[0] + '_' + srt_item['languageCode'] + '.srt'
                srt_url = srt_item['url']
                response = self.session.get(srt_url)
                fp = open(os.path.join(resource['savedir'], srt_name), 'wb')
                fp.write(response.content)
                fp.close()
    # --下載PDF
    elif resource['type'] == 'pdf':
        data = {
            't': '3',
            'cid': resource['contentId'],
            'unitId': resource['id'],
            'mob-token': self.infos_return['results']['mob-token'],
        }
        response = self.session.post('http://www.icourse163.org/mob/course/learn/v1', data=data)
        pdf_url = response.json()['results']['learnInfo']['textOrigUrl']
        self.defaultdownload({
            'download_url': pdf_url,
            'savedir': resource['savedir'],
            'savename': resource['savename'],
        })
    # --下載富文本
    elif resource['type'] == 'rich_text':
        download_url = 'http://www.icourse163.org/mob/course/attachment.htm?' + urlencode(resource['jsonContent'])
        self.defaultdownload({
            'download_url': download_url,
            'savedir': resource['savedir'],
            'savename': resource['savename'],
        })

ok，大功告成啦，寫(xiě)的有點(diǎn)簡(jiǎn)略，因?yàn)橥砩线€有點(diǎn)其他事。大家可以自己在手機(jī)端抓包試試，很簡(jiǎn)單的~

到此這篇關(guān)于利用Python制作一個(gè)MOOC公開(kāi)課下載器的文章就介紹到這了,更多相關(guān)Python公開(kāi)課下載器內(nèi)容請(qǐng)搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！

您可能感興趣的文章: