def get_source_list(tid):
# 2018.6 抓取的数据包没有 getMocTermDto.dwr，怀疑是MOOC改版了。只能通过查getLastLearnedMocTermDto.dwr得到资源列表
# 但是这就需要加入Cookie了，还要保持对话什么的...不是很方便，就暂时还用网络大神的老版本吧
# url = 'https://www.icourse163.org/dwr/call/plaincall/CourseBean.getLastLearnedMocTermDto.dwr' # POST请求，视频链接在r的js中
url = 'http://www.icourse163.org/dwr/call/plaincall/CourseBean.getMocTermDto.dwr' # 网络大神的旧链接
data = {
'callCount': '1',
'scriptSessionId': '${scriptSessionId}190',
'c0-scriptName': 'CourseBean',
'c0-methodName': 'getMocTermDto',
'c0-id': 0,
'c0-param0': 'number:' + tid, # tid,termId
'c0-param1': 'number:1',
'c0-param2': 'boolean:true',
'batchId': unixtime.now()
}
try:
r = requests.post(url, headers=headers, data=data)
r.raise_for_status()
# test.detect_encoding(r) # 检测到响应的编码时'ascii'
page = r.text.encode('utf-8').decode(
'unicode_escape') # 解码为 unicode_escape 便于print将汉字打印输出
# print(page[3000:4000]) # 测试所用
# test.outputHTML(page, '获取资源列表')
return page
except requests.HTTPError as ex:
print('>>> 课程搜索页面访问出错...\n[-]ERROR: %s' % str(ex))
raise
def test_main():
now = unixtime.now()
dtcurrent = unixtime.current_datetime()
tscurrent = unixtime.from_datetime(dtcurrent)
dtnow = unixtime.to_datetime(now)
tsnow = unixtime.from_datetime(dtnow)
assert round(now) == round(tsnow)
assert round(now) == round(tscurrent)
assert dtnow.isoformat().endswith("+00:00")
assert dtcurrent.isoformat().endswith("+00:00")
def get_download_info(dataList, sourceType, Quality=None, fileFormat=None):
url = 'http://www.icourse163.org/dwr/call/plaincall/CourseBean.getLessonUnitLearnVo.dwr'
content_id = dataList[0]
file_id = dataList[1]
file_name = re.sub(r'[/\\*|<>:?"]', '', dataList[2]) # 移除Windows文件名非法字符
data = {
'callCount': '1',
'scriptSessionId': '${scriptSessionId}190',
'c0-scriptName': 'CourseBean',
'c0-methodName': 'getLessonUnitLearnVo',
'c0-id': '0',
'c0-param0': 'number:' + content_id, # contentId
'c0-param1': 'number:{}'.format(sourceType),
'c0-param2': 'number:0',
'c0-param3': 'number:' + file_id, # 文件id
'batchId': unixtime.now()
}
try:
r = requests.post(url, headers=headers, data=data)
r.raise_for_status()
page = r.text
# test.outputHTML(page,'下载链接')
except requests.HTTPError as ex:
print('课程搜索页面访问出错...\n[-]ERROR: %s' % str(ex))
raise
if Quality: # 进行视频文件的解析
re_videoLink = r'{}{}Url="(.+?)";'.format(fileFormat, Quality)
video_url = re.findall(re_videoLink, page)
re_srtLink = r's\d+\.name="([\w\\]+?)";s\d+\.url="(.+?)";'
srt_url = re.findall(re_srtLink, page)
if video_url:
if srt_url:
return [video_url[0], srt_url[0][1]], file_name
else:
return [video_url[0]], file_name
else:
return [], file_name
else: # 进行课件文件的解析
re_PDFLink = r'http://nos.netease.com/.*?\.pdf'
pdf_url = re.findall(re_PDFLink, page)
if pdf_url:
return [pdf_url[0]], file_name
else:
return [], file_name
def msg(message):
message = "[" + str(unixtime.toDateString(
unixtime.now())) + "]" + " " + str(message)
if (config.output_place == config.output_console): print(message)