Get video links from chinesemooc.org

cnmooc.py

#!/usr/bin/env python3
from time import sleep
from collections import namedtuple
import json, re, os, csv
from urllib.parse import parse_qsl, urljoin, urlparse, urlencode
from requests import Session
from requests.cookies import create_cookie

parse_qs = lambda *args, **kwargs: dict(parse_qsl(*args, **kwargs))
Info = namedtuple("CourseInfo", ["name", "teacher"])
Lesson = namedtuple("Lesson", ["id", "no", "name"])
LessonWare = namedtuple("LessonWare", ["id", "name", "type", "lesson_id"])

VIDEO = '1'
ASGMT = '2'
FILE = '4'

BASE_URL = "http://www.chinesemooc.org"

class Course():
    def __init__(self, cookies: str, course_url: str):
        self.session = Session()
        cquery = parse_qs(course_url)
        self.course = {
                'kvideoid': cquery['kvideoid'],
                'classesid': cquery['classesid']
                }
        for cookie in cookies.split(";"):
            for k, v in parse_qs(cookie.strip()).items():
                #print(k ,v)
                self.session.cookies.set_cookie(create_cookie(name=k, value=v))
    
    _REGEX_COURSE_NAME = re.compile(r'<p class="course-info-title">\s*(.+)\s*</p>')
    _REGEX_COURSE_TEACHER = re.compile(r'<strong class="user-name">\s*(.+)\s*</strong>')
    def info(self):
        url = urljoin(BASE_URL, "/kvideo.php?do=course_progress&" + urlencode(self.course))   
        data = self.session.get(url).text
        #print(url, data)
        name = self._REGEX_COURSE_NAME.search(data).group(1)
        teacher = self._REGEX_COURSE_TEACHER.search(data).group(1)
        return Info(name, teacher)

    def lessons(self):
        url = urljoin(BASE_URL, "/api/player_course_list.php")
        data = json.loads(self.session.get(url + "?" + urlencode(self.course)).text)
        for lesson in data['msg']:
            yield Lesson(lesson['course_id'], lesson['order_num_str'], lesson['course_name'])

    def lesson_wares(self, lesson: Lesson):
        url = urljoin(BASE_URL, "/course.php?ac=course_live&op=live&")
        data = self.session.get(url + urlencode({'course_id': lesson.id})).text
        data = json.loads(data)
        #print(data)
        for ware in data['msg']['list']:
            yield LessonWare(ware['eid'], ware['subject'], ware['type'], lesson.id)
 
    def get_video(self, video: LessonWare):
        url = urljoin(BASE_URL, "/api/course_video_watch.php")
        url = url + "?" + urlencode({'course_id': video.lesson_id, 'eid': video.id})
        data = self.session.get(url).text
        #print(url, data)
        data = json.loads(data)
        videos = {'origin': data['msg']['mp4_url']}
        for _, video in data['msg']['transcode_succ_list']:
            videos[video['file_type']] = video['file_path']
        return videos
        

def main():
    cookies = input("Cookies: ")
    curl = input("Course URL with kvideoid and classesid: ")
    interval = int(input("Interval: ") or 5) 
    course = Course(cookies, curl)

    info = course.info()
    print(info)
    fpath = f"./{info.name} - {info.teacher}.csv"
    if os.path.exists(fpath):
        exit("File already existed: " + fpath)
    with open(fpath, "w") as f:
        w = csv.writer(f)
        w.writerow("#, Lesson, Name, Origin, LD, SD, HD, Others".split(", "))
        for lesson in course.lessons():
            print(lesson)
            for ware in course.lesson_wares(lesson):
                print(ware)
                if ware.type == VIDEO:
                    video = course.get_video(ware)
                    row = f"{lesson.no}, {lesson.name}, {ware.name}".split(", ")
                    row.append(video.pop('origin', ""))
                    row.append(video.pop('LD', ""))
                    row.append(video.pop('SD', ""))
                    row.append(video.pop('HD', ""))
                    if video:
                        others = []
                        for _, other in video.items():
                            others.append(other)
                        row.append(" ".join(others))
                    w.writerow(row)
                    sleep(interval)
                else:
                    print("(Ignored 1 course ware)")
            sleep(interval)

if __name__ == "__main__":
    main()