mirror of
https://github.com/soimort/you-get.git
synced 2025-01-23 21:45:02 +03:00
修复西瓜视频下载失败问题;
fix problem:the JSON object must be str, bytes or bytearray, not NoneType
This commit is contained in:
liguangbin
parent
699391135b
commit
15393a8218
@ -80,59 +80,94 @@ def get_video_url_from_video_id(video_id):
|
|||||||
return url
|
return url
|
||||||
|
|
||||||
|
|
||||||
def ixigua_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
|
def ixigua_download(url, output_dir='.', merge=True, info_only=False, stream_id='', **kwargs):
|
||||||
# example url: https://www.ixigua.com/i6631065141750268420/#mid=63024814422
|
# example url: https://www.ixigua.com/i6631065141750268420/#mid=63024814422
|
||||||
resp = urlopen_with_retry(request.Request(url))
|
headers['cookie'] = "MONITOR_WEB_ID=7892c49b-296e-4499-8704-e47c1b15123; " \
|
||||||
|
"ixigua-a-s=1; ttcid=af99669b6304453480454f1507011d5c234; BD_REF=1; " \
|
||||||
|
"__ac_nonce=060d88ff000a75e8d17eb; __ac_signature=_02B4Z6wo100f01kX9ZpgAAIDAKIBBQUIPYT5F2WIAAPG2ad; " \
|
||||||
|
"ttwid=1%7CcIsVF_3vqSIk4XErhPB0H2VaTxT0tdsTMRbMjrJOPN8%7C1624806049%7C08ce7dd6f7d20506a41ba0a331ef96a6505d96731e6ad9f6c8c709f53f227ab1"
|
||||||
|
|
||||||
|
resp = urlopen_with_retry(request.Request(url, headers=headers))
|
||||||
html = resp.read().decode('utf-8')
|
html = resp.read().decode('utf-8')
|
||||||
|
|
||||||
_cookies = []
|
_cookies = []
|
||||||
for c in resp.getheader('Set-Cookie').split("httponly,"):
|
for c in resp.getheader('Set-Cookie').split("httponly,"):
|
||||||
_cookies.append(c.strip().split(' ')[0])
|
_cookies.append(c.strip().split(' ')[0])
|
||||||
headers['cookie'] = ' '.join(_cookies)
|
headers['cookie'] += ';'.join(_cookies)
|
||||||
|
|
||||||
conf = loads(match1(html, r"window\.config = (.+);"))
|
match_txt = match1(html, r"<script id=\"SSR_HYDRATED_DATA\">window._SSR_HYDRATED_DATA=(.*?)<\/script>")
|
||||||
if not conf:
|
if not match_txt:
|
||||||
log.e("Get window.config from url failed, url: {}".format(url))
|
log.e("Get video info from url failed, url: {}".format(url))
|
||||||
return
|
return
|
||||||
verify_url = conf['prefix'] + conf['url'] + '?key=' + conf['key'] + '&psm=' + conf['psm'] \
|
video_info = loads(match_txt.replace('":undefined', '":null'))
|
||||||
+ '&_signature=' + ''.join(random.sample(string.ascii_letters + string.digits, 31))
|
if not video_info:
|
||||||
try:
|
log.e("video_info not found, url:{}".format(url))
|
||||||
ok = get_content(verify_url)
|
|
||||||
except Exception as e:
|
|
||||||
ok = e.msg
|
|
||||||
if ok != 'OK':
|
|
||||||
log.e("Verify failed, verify_url: {}, result: {}".format(verify_url, ok))
|
|
||||||
return
|
return
|
||||||
html = get_content(url, headers=headers)
|
|
||||||
|
|
||||||
video_id = match1(html, r"\"vid\":\"([^\"]+)")
|
title = video_info['anyVideo']['gidInformation']['packerData']['video']['title']
|
||||||
title = match1(html, r"\"player__videoTitle\">.*?<h1.*?>(.*)<\/h1><\/div>")
|
video_resource = video_info['anyVideo']['gidInformation']['packerData']['video']['videoResource']
|
||||||
if not video_id:
|
if video_resource.get('dash', None):
|
||||||
log.e("video_id not found, url:{}".format(url))
|
video_list = video_resource['dash']
|
||||||
|
elif video_resource.get('dash_120fps', None):
|
||||||
|
video_list = video_resource['dash_120fps']
|
||||||
|
elif video_resource.get('normal', None):
|
||||||
|
video_list = video_resource['normal']
|
||||||
|
else:
|
||||||
|
log.e("video_list not found, url:{}".format(url))
|
||||||
return
|
return
|
||||||
video_info_url = get_video_url_from_video_id(video_id)
|
|
||||||
video_info = loads(get_content(video_info_url))
|
streams = [
|
||||||
if video_info.get("code", 1) != 0:
|
# {'file_id': 'fc1b9bf8e8e04a849d90a5172d3f6919', 'quality': "normal", 'size': 0,
|
||||||
log.e("Get video info from {} error: server return code {}".format(video_info_url, video_info.get("code", 1)))
|
# 'definition': '720p', 'video_url': '','audio_url':'','v_type':'dash'},
|
||||||
return
|
]
|
||||||
if not video_info.get("data", None):
|
# 先用无水印的视频与音频合成，没有的话，再直接用有水印的mp4
|
||||||
log.e("Get video info from {} error: The server returns JSON value"
|
if video_list.get('dynamic_video', None):
|
||||||
" without data or data is empty".format(video_info_url))
|
audio_url = base64.b64decode(
|
||||||
return
|
video_list['dynamic_video']['dynamic_audio_list'][0]['main_url'].encode("utf-8")).decode("utf-8")
|
||||||
if not video_info["data"].get("video_list", None):
|
dynamic_video_list = video_list['dynamic_video']['dynamic_video_list']
|
||||||
log.e("Get video info from {} error: The server returns JSON value"
|
streams = convertStreams(dynamic_video_list, audio_url)
|
||||||
" without data.video_list or data.video_list is empty".format(video_info_url))
|
elif video_list.get('video_list', None):
|
||||||
return
|
dynamic_video_list = video_list['video_list']
|
||||||
if not video_info["data"]["video_list"].get("video_1", None):
|
streams = convertStreams(dynamic_video_list, "")
|
||||||
log.e("Get video info from {} error: The server returns JSON value"
|
|
||||||
" without data.video_list.video_1 or data.video_list.video_1 is empty".format(video_info_url))
|
print("title: %s" % title)
|
||||||
return
|
for stream in streams:
|
||||||
bestQualityVideo = list(video_info["data"]["video_list"].keys())[-1] #There is not only video_1, there might be video_2
|
if stream_id != "" and stream_id != stream['definition']:
|
||||||
size = int(video_info["data"]["video_list"][bestQualityVideo]["size"])
|
continue
|
||||||
print_info(site_info=site_info, title=title, type="mp4", size=size) # 该网站只有mp4类型文件
|
|
||||||
if not info_only:
|
print(" - format: %s" % stream['definition'])
|
||||||
video_url = base64.b64decode(video_info["data"]["video_list"][bestQualityVideo]["main_url"].encode("utf-8"))
|
print(" size: %s MiB (%s bytes)" % (round(stream['size'] / 1048576, 1), stream['size']))
|
||||||
download_urls([video_url.decode("utf-8")], title, "mp4", size, output_dir, merge=merge, headers=headers, **kwargs)
|
print(" quality: %s " % stream['quality'])
|
||||||
|
print(" v_type: %s " % stream['v_type'])
|
||||||
|
# print(" video_url: %s " % stream['video_url'])
|
||||||
|
# print(" audio_url: %s " % stream['audio_url'])
|
||||||
|
print()
|
||||||
|
|
||||||
|
# 不是只看信息的话，就下载第一个
|
||||||
|
if not info_only:
|
||||||
|
urls = [stream['video_url']]
|
||||||
|
if stream['audio_url'] != "":
|
||||||
|
urls.append(stream['audio_url'])
|
||||||
|
kwargs['av'] = 'av'
|
||||||
|
download_urls(urls, title, "mp4", stream['size'], output_dir, merge=merge, headers=headers,
|
||||||
|
**kwargs)
|
||||||
|
return
|
||||||
|
|
||||||
|
|
||||||
|
def convertStreams(video_list, audio_url):
|
||||||
|
streams = []
|
||||||
|
for dynamic_video in video_list:
|
||||||
|
streams.append({
|
||||||
|
'file_id': dynamic_video['file_hash'],
|
||||||
|
'quality': dynamic_video['quality'],
|
||||||
|
'size': dynamic_video['size'],
|
||||||
|
'definition': dynamic_video['definition'],
|
||||||
|
'video_url': base64.b64decode(dynamic_video['main_url'].encode("utf-8")).decode("utf-8"),
|
||||||
|
'audio_url': audio_url,
|
||||||
|
'v_type': dynamic_video['vtype'],
|
||||||
|
})
|
||||||
|
|
||||||
|
return streams
|
||||||
|
|
||||||
|
|
||||||
def ixigua_download_playlist_by_url(url, output_dir='.', merge=True, info_only=False, **kwargs):
|
def ixigua_download_playlist_by_url(url, output_dir='.', merge=True, info_only=False, **kwargs):
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user