def run(self):
self._lock.acquire()
common.any_download(url=self._url,
info_only=False,
output_dir=self._save_path,
merge=True)
self._lock.release()
def __init__(self, aid, parser='lxml'):
self.filename = str(aid)
self.video_url = None
self.xml = True
self.parser = parser
self.aid = aid
self.cid = None
self.videolength = None
self.finished = False
self.error = False
ensure_dir('dataset/' + self.filename)
# self.get_cid(self.aid)
try:
self.set_url(self.aid)
self.get_videoInfo(self.aid)
if self.videolength >= 300:
shutil.rmtree('dataset/' + self.filename)
print('Delete', self.filename)
return
yg.any_download(self.video_url,
output_dir='./dataset/' + str(self.filename),
caption=False)
self.get_danmu(self.cid)
self.get_comment(self.aid)
except (Exception) as e:
print('something serious happened ->', )
print(e)
self.error = True
if self.error == True:
self.finished = False
shutil.rmtree('dataset/' + self.filename)
print('Delete', self.filename)
else:
self.finished = True
def download_video_limit_size(url,
output_dir='.',
minsize=0,
maxsize=float('inf')): # 限制视频大小方便处理
def get_info_from_url(url): # 这里的挂钩不适用于多线程
m, url = url_to_module(url)
jdata = None
_org_print = print
def _new_print(*a, **k):
nonlocal jdata
try:
jdata = json.loads(a[0])
except:
pass
builtins.print = _new_print
m.download(url, merge=True, output_dir='.', info_only=False)
builtins.print = _org_print
return jdata
with gt:
you_get.common.json_output = True # 开启仅显示json文件
info = get_info_from_url(url)
size = info['streams']['__default__']['size'] / (2**20) # 使用的单位是M(兆)
if size and size > minsize and size < maxsize:
you_get.common.json_output = False # 关闭仅显示json文件
any_download(url,
output_dir=output_dir,
merge=True,
info_only=False)
return info
def download_video(url, save_path):
# 线程锁
# lock = Lock()
# lock.acquire()
common.any_download(url=url,
info_only=False,
output_dir=save_path,
merge=True)
def you_get_download(url):
if url.find('bilibili') != -1:
if os.path.exists(cookies_file_path):
you_get.load_cookies(cookies_file_path)
you_get.any_download(url=url,
info_only=False,
output_dir=origin_video_dir,
merge=True)
def download_url(url: str, itag: int, output_dir: Optional[str],
on_complete: callable):
s = StringIO()
with redirect_stdout(s):
any_download(url,
stream_id=str(itag),
output_dir=output_dir,
merge=True)
on_complete()
def downloadMgtvVideo(url, outputDir, streamId="ld"):
args = {
'stream_id': streamId,
'output_dir': outputDir,
'merge': True,
'info_only': False,
'json_output': False,
'caption': True
}
any_download(url, **args)
def post(self):
url = request.form['url']
sys.stdout.buffer = []
any_download(url, info_only=True, output_dir='.', merge=False)
text_area = sys.stdout
format_list = []
for s in text_area.buffer:
for str in s:
if re.findall(r'(\s*- format:.*)', str):
format_list.append(str.strip()[9:].strip())
return {'format': format_list}
def get_url_options(url: str) -> Result:
s = StringIO()
with redirect_stdout(s):
any_download(url, info_only=True, json_output=True)
url_options = json.loads(s.getvalue())
title = url_options["title"]
itags = []
for itag, data in url_options['streams'].items():
itags.append(_parse_itag(data))
itags.sort(key=lambda i: i.x * i.y, reverse=True)
itags = [i for i in itags if i.x > 0 and i.y > 0]
return Result(title=title, itags=itags)
def get_info(url):
result = None
try:
result = you_get.any_download(url, json_output=True)
except Exception as e:
print(type(e), e)
return result
def post(self):
try:
time1 = time.time()
url = request.form['url']
sys.stdout.buffer = []
if 'format' in request.form:
ft = request.form['format']
any_download(url, info_only=False, output_dir='.',
merge=False, format=ft)
else:
any_download(url, info_only=False, output_dir='.',
merge=False)
text_area = sys.stdout
api_list = ''
for s in text_area.buffer:
for str in s:
if re.findall(r'(http://[^?]+)', str):
api_list = str
if 'time' in request.form:
if request.form['time']:
urls_json = []
video_list = api_list.replace("'", "").split(',')
for index in range(len(video_list)):
u = video_list[index].strip()
video_json = json.loads(getVideoJsonInfo("%s" % u))
time_length = video_json['format']['duration']
file_size = video_json['format']['size']
urls_json.append({
"size": file_size,
"seconds": time_length,
"number": index,
"url": u
})
time2 = time.time()
return {'url': urls_json,
'parse_time': time2 - time1}
time2 = time.time()
return {'url': api_list,
'parse_time': time2 - time1}
except:
return {'error': 'args error',
'code': 404}
from you_get import common
common.any_download(url='https://v.youku.com/v_show/id_XNDgxMDk2Nzg0OA==.html',
info_only=False,
output_dir=r'video',
merge=True)
# _*_ encoding:utf-8 _*_
"""
pip install you-get
https://you-get.org/
"""
__author__ = "aaron.qiu"
from you_get.common import any_download
from you_get.__main__ import main_dev
if __name__ == '__main__':
any_download(url="https://www.youtube.com/watch?v=QuPiZ86EFhQ",
output_dir="E:\\",
merge="E:\\")
# any_download(url="https://www.youtube.com/watch?v=jNQXAC9IVRw", output_dir="E:\\", merge="E:\\")
choose_hint = "请输入您要进行的操作序号：\n\n{}\n{}\n{}\n{}\n{}\n{}\n".format(
"1、视频下载一条龙", "2、本地视频一条龙", "3、视频转音频", "4、音频分割", "5、字幕提取", "6、字幕拼接")
print(choose_hint)
choose_input = input()
if choose_input == "1":
print("请输入要下载的地址")
while True:
download_url = input()
result = url_match_pattern.match(download_url)
if result is not None:
if download_url.find("bilibili") != -1:
download_bilibli_video(download_url)
break
else:
you_get.any_download(url=download_url,
info_only=False,
output_dir=video_before_dir)
break
else:
print("URL格式错误，请输入正确的URL")
# 扫描flv文件
flv_list = cp_utils.filter_file_type(video_before_dir, ".flv")
print(flv_list)
elif choose_input == "2":
flv_list = cp_utils.filter_file_type(video_before_dir, ".flv")
if len(flv_list) == 0:
print("本地视频为空，请检查后重试：")
else:
print("请选择处理视频的序号：\n{}\n".format("=" * 64))
for index, value in enumerate(flv_list):
print("{}.{}".format(index, value))
def download_one(self, url):
common.any_download(url=url,
info_only=False,
output_dir=self.savepath,
merge=True)
