def get_content(self, section_id):
"""
获取章节内容
:params section_id: 章节url
:params u: 章节url
"""
resp = json.loads(
network_connect(
self.section_api_url.format(self.class_id, section_id)).text)
# {'code': 403, 'data': [], 'msg': '哎呀，课程内容丢失了'}
code = resp.get("code", None)
if code == None or code != 200:
return False
else:
content_data = resp.get("data", [])
if content_data == []:
return False
else:
nodes = content_data["nodes"]
# 原生html代码
text_list = [
node["content"] if node["content_type"] == 1 else
node["content"]["content"]
if node["content_type"] == 3 else "" for node in nodes
]
# video_id列表
video_id_list = [
node["content"]["id"] for node in nodes
if node["content_type"] == 2
]
return text_list, video_id_list
def get_stage_data(self):
"""
获取每个章节的数据
:params class_id:课程id
:return :课程data
[{'stage_id': 1899, 'stage_name': '课前内容'},...]
"""
class_id = self.class_id
res = json.loads(
network_connect(self.class_api_url.format(class_id)).text)
code = res.get("code", None)
if code == None or code == 0:
return False
else:
study_stage_data = res.get("data", [])
if study_stage_data == []:
return False
else:
self.class_name = study_stage_data["class_name"]
stage_data = [{
"stage_id": i["stage_id"],
"stage_name": i["stage_name"]
} for i in study_stage_data["study_stage"]
if i["is_lock"] == 0]
return stage_data
def get_m3u8_key(self):
with open(self.m3u8_path, "r", encoding="utf8") as f:
for i in f.readlines():
if "EXT-X-KEY" in i:
key_url = i.split('URI="')[1].split('"')[0]
if key_url != self.key_url:
return self.key_url, network_connect(key_url).content
def get_ts(self):
with open(self.m3u8_path, "r", encoding="utf8") as f:
r = f.readlines()
for i in range(len(r)):
if "#EXTINF" in r[i]:
ts_url = r[i + 1].replace("\n", "")
ts_name = r[i + 1].replace("\n",
"").split("?")[0].split("/")[-1]
print("\rTS文件下载中...({}/{}){}".format(i, len(r), ts_name),
end="")
self.ts_list.append(ts_name)
resp = network_connect(ts_url).content
self.down_ts(ts_name, resp)
def main(self, video_path, audio_matser_url):
"""
:params video_path:视频存储路径.H:\test.mp4
:params audio_matser_url:视频地址
"""
# audio_matser_url-media_rates_url
# 视频地址-码率链接列表(down)-高码率m3u8(down)-get加密key-下载ts(down)-合并ts
# 存在则跳过SV流程
if os.path.exists(video_path):
print(video_path, "已存在")
return
self.ts_list = []
self.sv_path = video_path.rsplit("\\", 1)[0]
video_id = audio_matser_url.split("video_id=")[-1]
media_rates_url = self.get_m3u8_url(audio_matser_url)
if media_rates_url == None:
print("获取media_rates_url失败 audio_matser_url: ", audio_matser_url)
return
self.high_rate_m3u8_url = self.parse_rate(media_rates_url)
if self.high_rate_m3u8_url == "":
print("高码率视频m3u8链接获取失败 audio_matser_url: ", audio_matser_url)
return
# 高码率m3u8文件名称
self.high_rate_m3u8_name = self.high_rate_m3u8_url.split("?")[0].split(
"/")[-1]
# 以m3u8文件名前缀创建临时目录
self.m3u8_work_path = folder(self.sv_path, video_id)
# 高码率m3u8文件存储路径
self.m3u8_path = os.path.join(self.m3u8_work_path,
self.high_rate_m3u8_name)
# 下载高码率m3u8文件
self.down(self.m3u8_path,
network_connect(self.high_rate_m3u8_url).content)
self.key_url, self.key = self.get_m3u8_key()
if self.key == None:
print("m3u8Key获取失败: ", self.key)
return
self.cryptor = AES.new(self.key, AES.MODE_CBC, self.key)
self.get_ts()
self.ts2mp4(video_path)
# sjk = SJK_VIDEO()
# sjk.main(r"G:\python_code\test.mp4","https://service.sanjieke.cn/video/master/auth?video_id=xxxxx&class_id=2xxxx")
def parse_rate(self, media_rates_url):
media_m3u8_name = media_rates_url.split("?")[0].split("/")[-1]
media_m3u8_path = os.path.join(self.sv_path, media_m3u8_name)
self.down(media_m3u8_path, network_connect(media_rates_url).content)
high_rate_m3u8_url = ""
with open(media_m3u8_path, "r", encoding="utf8") as f:
r = f.readlines()
for i in range(len(r)):
if "#EXT-X-STREAM-INF" in r[i]:
# 只取第一个高码率的地址
high_rate_m3u8_url = r[i + 1].replace("\n", "")
break
# 删除多码率列表文件
os.remove(media_m3u8_path)
return high_rate_m3u8_url
def get_section_data(self, stage_id):
"""
获取每个card里的文章数据
:parmas stage_id: 章节id
:return: 章节数据,
"""
u = self.stage_api_url.format(self.class_id, stage_id)
res = json.loads(network_connect(u).text)
code = res.get("code", None)
if code == None or code == 0:
return False
else:
study_section_data = res.get("data", [])
if study_section_data == []:
return False
else:
section_data = [{
"card_name": i["card_name"],
"section_id": j["section_id"],
"section_name": j["section_name"]
} for i in study_section_data["nodes"] for j in i["children"]]
return section_data
def get_m3u8_url(self, audio_matser_url):
resp = json.loads(network_connect(audio_matser_url).text)
if resp.get("code", None) == 200:
return resp["data"]["url"]
else:
return None