网易公开课下载脚本

downlaod_xunlei.py

# https://www.twblogs.net/a/5bdf0e822b717720b51c3328/zh-cn
# https://www.bilibili.com/read/cv1624058/

import os
import sys
import requests
import time
from lxml import html
from you_get.common import r1, get_decoded_html
from win32com.client import Dispatch

def resource_url(url):
    html = get_decoded_html(url)
    url = (r1(r'["\'](.+)-list.m3u8["\']', html) or r1(r'["\'](.+).m3u8["\']', html)) + ".mp4"
    return url

def target_resource(course_url):
    res = requests.get(course_url)
    tree = html.fromstring(res.text)

    # Filename list
    file_index_list = tree.xpath('//div[@class="m-mn"]//table[2]//tr/td[1]/text()')
    filename_list = tree.xpath('//div[@class="m-mn"]//table[2]//tr/td[1]/a/text()')
    file_index_list = list(map(lambda x:x.strip(), file_index_list))
    file_index_list = [i for i in file_index_list if i]
    filename_list = list(map(lambda i, x:'%s %s.mp4' % (i.strip(), x.strip()), file_index_list, filename_list))

    # URL list
    page_url_list = tree.xpath('//div[@class="m-mn"]//table[2]//tr/td[1]/a//@href')
    page_url_list = list(map(lambda x:x.strip().replace('open.163.com', 'v.163.com'), page_url_list))
    resource_url_list = list(map(lambda x: resource_url(x), page_url_list))

    return list(map(lambda x, y: { 'filename': x, 'url': y }, filename_list, resource_url_list))


def dispatchXunLei(download_url, save_as, file_path):
    xunlei = Dispatch("ThunderAgent.Agent64.1")
    print(download_url, save_as, file_path)
    xunlei.AddTask(download_url, save_as, file_path, "", "", -1, 0, 5)
    xunlei.CommitTasks()

url = sys.argv[1]
data = target_resource(url)
for i in range(len(data)):
    dispatchXunLei(data[i]['url'], data[i]['filename'], sys.argv[2])
    time.sleep(0.5)

download.py

# pip install requests lxml you-get

import os
import requests
from lxml import html
from you_get.common import r1, get_decoded_html

def resource_url(url):
    html = get_decoded_html(url)
    url = (r1(r'["\'](.+)-list.m3u8["\']', html) or r1(r'["\'](.+).m3u8["\']', html)) + ".mp4"
    return url

# Course info
course_path = 'http://open.163.com/special/opencourse/financialtheory.html'
ext = 'mp4'

res = requests.get(course_path)
tree = html.fromstring(res.text)

# Filename list
file_index_list = tree.xpath('//div[@class="m-mn"]//table[2]//tr/td[1]/text()')
filename_list = tree.xpath('//div[@class="m-mn"]//table[2]//tr/td[1]/a/text()')
file_index_list = list(map(lambda x:x.strip(), file_index_list))
file_index_list = [i for i in file_index_list if i]

filename_list = list(map(lambda i, x:'%s %s' % (i.strip(), x.strip()), file_index_list, filename_list))
print("Here are your courses:")
print(*filename_list, sep='\n')

# URL list
page_url_list = tree.xpath('//div[@class="m-mn"]//table[2]//tr/td[1]/a//@href')
page_url_list = list(map(lambda x:x.strip().replace('open.163.com', 'v.163.com'), page_url_list))

resource_url_list = list(map(lambda x: resource_url(x), page_url_list))
print("\nHere are the resources:")
print(*resource_url_list, sep='\n')


for i in range(len(resource_url_list)):
    print("Download %s at %s" % (filename_list[i], resource_url_list[i]))
    os.system(r'curl {} --output "{}".{}'.format(resource_url_list[i], filename_list[i], ext))