def train(self, train_id):
self.train_id = train_id
train_start = time.time()
train = self.get_train_info()
train_name = train['name']
self.path += '/' + train_name
cto.check_or_make_dir(self.path)
print(u'微职位名称:' + train_name + u'\n获取课程列表')
courses = train['courses']
total_course = len(courses)
print('总计%d门course' % total_course)
# 打印course名称
for course in courses:
print course
print(str(courses.index(course) + 1) + '.' + course['course_name'])
action = raw_input('是否下载y/n? 默认y:')
# action = 'y'
if action == 'n':
print '终止下载,程序退出'
exit()
# 保留train index page
url = 'http://edu.51cto.com/center/wejob/index/view?id=%d&force=3&orig=try' % (
self.train_id)
resp = self.session.get(url)
with open(self.path + '/index.html', 'ab') as f:
f.write(resp.content)
# 将课程信息保存到json中去
with open(self.path + '/info.json', 'w') as f:
data = json.dumps(courses, ensure_ascii=False, indent=2)
f.write(data)
for course in courses:
course_id = int(course['train_course_id'])
course_index = courses.index(course) + 1
file_path = os.path.join(
self.path, course['number'] + '.' + course['course_name'])
cto.check_or_make_dir(file_path)
train_introduce = 'http://edu.51cto.com/center/wejob/index/view?id=%d&force=3&orig=try' % (
self.train_id)
train_page = self.session.get(train_introduce)
with open(file_path + '/index.html', 'ab') as f:
f.write(train_page.content)
print('%d/%d获取%s详情' %
(course_index, total_course, course['course_name']))
lessons = self.get_course_info(course_id)
total_lesson = len(lessons)
for lesson in lessons:
lesson_type = lesson["lesson_type"]
lesson_name = lesson['lesson_name']
if lesson_type != "1":
print u"跳过练习 " + lesson_name
continue
lesson_id = '_'.join(
[str(course_id), str(lesson['lesson_id'])])
show_number = lesson["show_number"]
lesson_path = os.path.join(
file_path, lesson["chapter_sort_name"],
"%s.%s" % (show_number, lesson['lesson_name']))
cto.check_or_make_dir(lesson_path)
# filename = os.path.join(file_path, "%d.%s.ts" % (show_number, lesson['lesson_name']))
# if os.path.exists(filename):
# continue
print datetime.datetime.now().strftime(
"%H:%M:%S") + ' 正在下载(%s/%d)-%s' % (
show_number, total_lesson, lesson['lesson_name'])
#qxx 下载、保存m3u8文件
m3u8_file = os.path.join(lesson_path, "vedio.m3u8")
if not os.path.exists(m3u8_file):
m3u8_content = self.get_m3u8_content(
lesson_id, lesson['video_id'])
with open(m3u8_file, 'w') as file:
file.write(m3u8_content)
#qxx 下载、保存enkey(加密key)文件
enkey_file = os.path.join(lesson_path, "enkey.key")
if not os.path.exists(enkey_file):
enkey_content = self.get_enkey(lesson_id,
lesson['video_id'])
with open(enkey_file, 'w') as file:
file.write(enkey_content)
#qxx 解密、保存key
key_file = os.path.join(lesson_path, "key.key")
if not os.path.exists(key_file):
key_content = decode_helper.decode(
enkey_content, lesson_id)
with open(key_file, 'w') as file:
file.write(key_content)
# urls = self.get_download_urls(m3u8_content)
# try:
# cto.download(lesson_path, urls)
# except Exception :
# time.sleep(random.uniform(5,10))
# cto.download(lesson_path, urls)
print 'train下载用时总计' + cto.total_time(time.time() - train_start)
def train(self):
train_start = time.time()
train = self.get_train_info()
train_name = train['name']
self.path += '/' + train_name
cto.check_or_make_dir(self.path)
print('微职位名称:' + train_name + '\n获取课程列表')
courses = train['courses']
total_course = len(courses)
print('总计%d门course' % (total_course))
#打印course名称
for course in courses:
print(str(courses.index(course) + 1) + '.' + course['course_name'])
action = raw_input('是否下载y/n? 默认y:')
if action == 'n':
print '终止下载,程序退出'
exit()
#保留train index page
url = 'http://edu.51cto.com/center/wejob/index/view?id=%d&force=3&orig=try' % (
self.train_id)
resp = self.session.get(url)
with open(self.path + '/index.html', 'ab') as f:
f.write(resp.content)
#将课程信息保存到json中去
with open(self.path + '/info.json', 'w') as f:
data = json.dumps(courses, ensure_ascii=False, indent=2)
f.write(data)
for course in courses:
course_id = int(course['train_course_id'])
course_index = courses.index(course) + 1
file_path = os.path.join(
self.path, course['number'] + '.' + course['course_name'])
cto.check_or_make_dir(file_path)
train_introduce = 'http://edu.51cto.com/center/wejob/index/view?id=%d&force=3&orig=try' % (
self.train_id)
train_page = self.session.get(train_introduce)
with open(file_path + '/index.html', 'ab') as f:
f.write(train_page.content)
print('%d/%d获取%s详情' %
(course_index, total_course, course['course_name']))
lessons = self.get_course_info(course_id)
total_lesson = len(lessons)
for lesson in lessons:
lesson_id = '_'.join(
[str(course_id), str(lesson['lesson_id'])])
lesson_index = lessons.index(lesson) + 1
filename = os.path.join(
file_path,
"%d.%s.ts" % (lesson_index, lesson['lesson_name']))
if os.path.exists(filename):
continue
print datetime.datetime.now().strftime(
"%H:%M:%S") + ' 正在下载(%d/%d)-%s' % (
lesson_index, total_lesson, lesson['lesson_name'])
urls = self.get_download_url(lesson_id, lesson['video_id'])
try:
cto.download(filename, urls)
except Exception:
time.sleep(random.uniform(5, 10))
cto.download(filename, urls)
print 'train下载用时总计' + cto.total_time(time.time() - train_start)
def train(self, train_id):
self.train_id = train_id
train_start = time.time()
train = self.get_train_info()
train_name = train['name']
self.path += '/' + train_name
cto.check_or_make_dir(self.path)
print('微职位名称:' + train_name + '\n获取课程列表')
courses = train['courses']
total_course = len(courses)
print('总计%d门course' % total_course)
# 打印course名称
# for course in courses:
# print(str(course, encoding='utf-8'))
# print(str(courses.index(course) + 1) + '.' + course['course_name'])
action = raw_input('是否下载y/n? 默认y:')
if action == 'n':
print('终止下载,程序退出')
exit()
# 保留train index page
url = 'http://edu.51cto.com/center/wejob/index/view?id=%d&force=3&orig=try' % (
self.train_id)
resp = self.session.get(url)
with open(self.path + '/index.html', 'ab') as f:
f.write(resp.content)
# 将课程信息保存到json中去
# with open(self.path + '/info.json', 'w') as f:
# data = json.dumps(courses, ensure_ascii=False, indent=2)
# f.write(data)
for course in courses:
course_id = int(course['train_course_id'])
course_index = courses.index(course) + 1
file_path = os.path.join(
self.path,
str(course['number']) + '.' + str(course['course_name']))
cto.check_or_make_dir(file_path)
train_introduce = 'http://edu.51cto.com/center/wejob/index/view?id=%d&force=3&orig=try' % (
self.train_id)
train_page = self.session.get(train_introduce)
with open(file_path + '/index.html', 'ab') as f:
f.write(train_page.content)
print('%d/%d获取%s详情' %
(course_index, total_course, course['course_name']))
lessons = self.get_course_info(course_id)
total_lesson = len(lessons)
for lesson in lessons:
lesson_id = '_'.join(
[str(course_id), str(lesson['lesson_id'])])
lesson_index = lessons.index(lesson) + 1
filename = os.path.join(
file_path,
"%d.%s.ts" % (lesson_index, lesson['lesson_name']))
if os.path.exists(filename):
continue
print(datetime.datetime.now().strftime("%H:%M:%S") +
' 正在下载(%d/%d)-%s' %
(lesson_index, total_lesson, lesson['lesson_name']))
try:
urls, get_key_url = self.get_download_url(
lesson_id, lesson['video_id'])
except Exception as e:
print("解析m3u8地址保存，可能视频不存在")
continue
#print "lession_id", course_id," get key url:", get_key_url
play_key = le.Lesson(self.session).get_key_for_wejob(
lesson_id, course_id, get_key_url)
def func_decode(video_data):
#print "play_key:%s, lesson_id:%s, " % (play_key, lesson['lesson_id'])
return decory_video.Video().decory(play_key, lesson_id,
video_data)
try:
cto.download(filename, urls, func_decode=func_decode)
except Exception:
time.sleep(random.uniform(5, 10))
cto.download(filename, urls)
print('train下载用时总计' + cto.total_time(time.time() - train_start))