def get(url: str) -> dict:
result = Result()
try:
av = re.findall(av_number_pattern, url)
if av:
av = av[0]
else:
raise NotFoundException
url = f'https://www.bilibili.com/video/av{av}'
rep = requests.get(url, headers=headers, timeout=15)
if rep.status_code == 200:
cover_url = re.findall(cover_pattern, rep.text)
if cover_url:
if '@' in cover_url[0]:
cover_url[0] = cover_url[0][:cover_url[0].index('@')]
result.imgUrls.extend(cover_url)
video_url = re.findall(video_pattern, rep.text)
if video_url:
result.videoUrls.extend(video_url)
elif rep.status_code == 404:
raise NotFoundException
else:
raise ServerErrorException
except errors as e:
result.err = 1
result.msg = e.message
return result()
def get(url: str) -> dict:
result = Result()
try:
rep = requests.get(url, headers=headers, timeout=20)
if rep.status_code == 200:
text = rep.text
title = re.findall(title_re, text)
if title:
result.videoName = title[0]
mp4_720p_mp4 = re.findall(mp4_720p_mp4_re, text)[0]
if mp4_720p_mp4:
result.videoUrls.extend(mp4_720p_mp4)
mp4_hd_mp4 = re.findall(mp4_hd_mp4_re, text)
if mp4_hd_mp4:
result.videoUrls.extend(mp4_hd_mp4)
mp4_ld_mp4 = re.findall(mp4_ld_mp4_re, text)
if mp4_ld_mp4:
result.videoUrls.extend(mp4_ld_mp4)
else:
raise NotFoundException
except errors as e:
result.err = 1
result.msg = e.message
return result()
def get(url: str) -> dict:
result = Result()
a = Wangyiyun()
play_url = a.get(url)
if play_url:
result.audioUrls.append(play_url)
else:
result.err = 1
result.msg = "未知错误"
return result()
def _get_not_logged(url: str) -> dict:
result = Result()
headers = {
"accept": "application/json",
"accept-encoding": "gzip, deflate, br",
"accept-language": "zh-CN,zh;q=0.9",
"content-length": "63",
"content-type": "application/json",
"cookie":
"pgv_pvi=9657849856; pgv_pvid=2069474799; RK=aHJszqfoXm; ptcz=0fc0035b9509215f060561393c09f6cde3bccc1953e79c2b5b1ec450e4e67f19; LW_uid=s1i5E5d4v2a1p5n702J1O2y0q8; eas_sid=M1k5T5N4O28185X7J291x2K1A3; o_cookie=286183317; pac_uid=1_286183317; ied_qq=o0286183317; LW_sid=x1Y5D6W4h4H516F6X9l9V8S8Z3; tvfe_boss_uuid=fbb4b39b5afeb49b; psrf_qqopenid=A140C50D3D791392EA89131C8B01FE1D; psrf_qqaccess_token=D2F43F3C25900E66193345D276AF9559; psrf_qqrefresh_token=E48409D7E8E4F3D5C3869F104380AB3E; psrf_qqunionid=002C01991CFB436BCD8A27A0EE1DB9FF; qm_keyst=Q_H_L_2ajiOt50eapmue6Eg1-l_W6XztEBr_u0vZJAPs4xctJZNJdsEZONiDnNJ206icA; psrf_musickey_createtime=1574482649; psrf_access_token_expiresAt=1582258649; person_id_bak=5295507715828209; person_id_wsbeacon=5689667751647505; wsreq_logseq=336060008",
"origin": "https://h5.weishi.qq.com",
"referer": url,
"sec-fetch-mode": "cors",
"sec-fetch-site": "same-origin",
"user-agent":
"Mozilla/5.0 (iPhone; CPU iPhone OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B137 Safari/601.1",
"x-requested-with": "XMLHttpRequest",
}
post_url = "https://h5.weishi.qq.com/webapp/json/challenge_feedrank/GetChallengeFeedDetail?t=0.2602280426206063&g_tk="
# request payload {"feedid":"6YV0vjeP71IHTsV08","challenge_id":"100026","type":0}
# get feedid, challenge_id
query = parse_qs(urlparse(url).query)
feedid = query.get('feedid')[0]
challenge_id = query.get('challegeid')[0]
# create request payload
payload = {
"feedid": feedid,
"challenge_id": challenge_id,
"type": 0,
}
# get data
with requests.post(post_url,
headers=headers,
data=json.dumps(payload),
timeout=33) as rep:
if rep.status_code == 200:
# print(rep.json())
data = rep.json().get('data')
# print(data.get('feedinfos'))
video_info = data.get('feedinfos')[0]
title = video_info.get("feed_desc")
play_url = video_info.get("video_url")
result.videoName = title
result.videoUrls.append(play_url)
return result()
def get(url: str) -> dict:
result = Result()
headers = {
"user-agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36",
}
video_info_url = "https://lens.zhihu.com/api/v4/videos/{id}"
ids = []
urls = []
rep = rs.get(url, headers=headers)
if rep.status_code == 200:
ids = re.findall(r'https://www.zhihu.com/video/(\d{1,})', rep.text)
if ids:
for id in ids:
rep = rs.get(video_info_url.format(id=id), headers=headers)
if rep.status_code == 200:
data = rep.json()
playlist = data.get("playlist")
temp = playlist.get("HD") or playlist.get(
"SD") or playlist.get("LD")
if temp:
url = temp.get("play_url")
urls.append(url)
result.videoUrls.extend(urls)
return result()
def get(url: str) -> dict:
result = Result()
pid = int(url[33:]) # get pid
post_data = {
"pid": pid,
"type": "post",
}
with requests.post(POST_URL,
headers=HEADERS,
data=json.dumps(post_data),
timeout=20) as rep:
if rep.status_code == 200:
data = rep.json()
# 下面处理很乱，主要对着返回数据看就很简单
id = data.get('data').get('post').get('imgs')[0].get('id')
if id:
play_url = data.get('data').get('post').get('videos').get(
str(id)).get('url')
if not play_url:
play_url = ""
else:
play_url = ""
# --------------------------------------------------------------
else:
play_url = ""
result.videoUrls.append(play_url)
return result()
def _get_logged(url: str) -> dict:
result = Result()
headers = {
'accept': 'application/json',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9',
'content-length': '84',
'content-type': 'application/json',
'cookie':
'pgv_pvi=9657849856; pgv_pvid=2069474799; RK=aHJszqfoXm; ptcz=0fc0035b9509215f060561393c09f6cde3bccc1953e79c2b5b1ec450e4e67f19; LW_uid=s1i5E5d4v2a1p5n702J1O2y0q8; eas_sid=M1k5T5N4O28185X7J291x2K1A3; o_cookie=286183317; pac_uid=1_286183317; ied_qq=o0286183317; LW_sid=x1Y5D6W4h4H516F6X9l9V8S8Z3; tvfe_boss_uuid=fbb4b39b5afeb49b; psrf_qqopenid=A140C50D3D791392EA89131C8B01FE1D; psrf_qqaccess_token=D2F43F3C25900E66193345D276AF9559; psrf_qqrefresh_token=E48409D7E8E4F3D5C3869F104380AB3E; psrf_qqunionid=002C01991CFB436BCD8A27A0EE1DB9FF; qm_keyst=Q_H_L_2ajiOt50eapmue6Eg1-l_W6XztEBr_u0vZJAPs4xctJZNJdsEZONiDnNJ206icA; psrf_musickey_createtime=1574482649; psrf_access_token_expiresAt=1582258649; person_id_bak=5295507715828209; person_id_wsbeacon=5689667751647505; wsreq_logseq=336060019',
'origin': "https://h5.weishi.qq.com",
'referer': url,
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'user-agent':
'Mozilla/5.0 (iPhone; CPU iPhone OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B137 Safari/601.1',
'x-requested-with': 'XMLHttpRequest',
}
post_url = "https://h5.weishi.qq.com/webapp/json/weishi/WSH5GetPlayPage?t=0.16820895093158983&g_tk="
# get feedid(id)
query = parse_qs(urlparse(url).query)
feedid = query.get('id')[0]
payload = {
"feedid": feedid,
"recommendtype": 0,
"datalvl": "all",
"_weishi_mapExt": {}
}
with requests.post(post_url,
headers=headers,
data=json.dumps(payload),
timeout=33) as rep:
if rep.status_code == 200:
# print(rep.json())
data = rep.json().get('data')
# print(data.get('feedinfos'))
video_info = data.get('feeds')[0]
title = video_info.get("feed_desc")
play_url = video_info.get("video_url")
result.videoName = title
result.videoUrls.append(play_url)
return result()
def get(url: str) -> dict:
result = Result()
try:
rep = requests.get(url, headers=headers, timeout=10)
if rep.status_code == 200:
html = rep.text
author = re.findall(author_pattern, html)
if author:
result.author = author[0]
audio_name = re.findall(audio_name_pattern, html)
if audio_name:
result.audioName = audio_name[0]
audio_url = re.findall(audio_url_pattern, html)
if audio_url:
result.audioUrls.extend(audio_url)
else:
result.err = 1
elif rep.status_code == 404:
raise NotFoundException
else:
raise ServerErrorException
except errors as e:
result.err = 1
result.msg = e.message
return result()
def get(url: str) -> dict:
result = Result()
try:
id = re.findall(r'([0-9]{1,})', url)
if id:
id = id[0]
else:
raise NotFoundException
# 得到最高品质以及歌曲信息
rep = requests.get(song_info_url.format(id=id),
headers=headers,
timeout=11)
if rep.status_code == 200:
best_quality = rep.json().get('data').get('songinfo').get(
'coopFormats')[0]
author = rep.json().get('data').get('songinfo').get('artist')
song_name = rep.json().get('data').get('songinfo').get('songName')
result.author = author
result.audioName = song_name
if not best_quality: best_quality = '128kmp3'
# 得到歌曲链接
rep2 = requests.get(mp3_url.format(id=id, quality=best_quality))
if rep2.status_code == 200:
play_url = rep.json().get('url', '')
result.audioUrls.append(play_url)
else:
result.msg = "歌曲链接没能得到"
except errors as e:
result.err = 1
result.msg = e.message
return result()
def get(url: str) -> dict:
result = Result()
try:
path = urlparse(url).path
voiceId = path.split("/")[-1]
if not voiceId:
raise NotFoundException
rep = rs.get(info_url.format(id=voiceId), headers=headers, timeout=11)
if rep.status_code == 200:
info = rep.json()
if info['code'] == 0:
userName = info.get("data").get("userVoice").get("userInfo").get("name")
voiceName = info.get("data").get("userVoice").get("voiceInfo").get("name")
voiceUrl= info.get("data").get("userVoice").get("voicePlayProperty").get("trackUrl")
result.author = userName
result.audioName = voiceName
result.audioUrls.append(voiceUrl)
else:
raise SpecialErrorException
else:
raise NotFoundException
except errors as e:
result.err = 1
result.msg = e.message
return result()
def get(url: str) -> dict:
result = Result()
try:
with requests.get(url=url, headers=HEADERS, timeout=50) as rep:
if rep.status_code == 200:
html = rep.text
singer = re.findall(SINGER_PATTERN, html)
if singer:
singer = singer[0]
result.author = singer
song_name = re.findall(SONG_NAME_PATTERN, html)
if song_name:
song_name = song_name[0]
result.audioName = song_name
play_url = re.findall(PLAY_URL_PATTERN, html)
if play_url:
result.audioUrls.extend(play_url)
play_video = re.findall(PLAY_VIDEO_PATTERN, html)
if play_video:
result.videoUrls.extend(play_video)
else:
raise NotFoundException
except errors as e:
result.err = 1
result.msg = e.message
return result()
def get(share_url) -> dict:
result = Result()
try:
# get share_url location
rep1 = requests.get(share_url, headers=headers, timeout=10)
share_url = rep1.headers.get('location', share_url)
# get html_text
rep2 = requests.get(share_url, headers=headers, timeout=10)
html_text = rep2.text
title = re.findall(title_pattern, html_text)
if title:
result.videoName = title[0]
play_url = re.findall(play_url_pattern, html_text)
if play_url:
play_url = play_url[0].replace('playwm', 'play')
# get video_url
rep3 = requests.get(play_url,
headers=headers,
allow_redirects=False,
timeout=30)
video_url = rep3.headers.get('location')
if video_url:
result.videoUrls.append(video_url)
else:
result.msg = "视频未能解析成功"
except errors as e:
result.err = 1
result.msg = e.message
return result()
def get(url: str) -> dict:
try:
result = Result()
headers = {
"Connection":
"keep-alive",
"Content-Length":
"209",
"Content-Type":
"text/plain;charset=UTF-8",
"Cookie":
"Hm_lvt_414bd23f4090657a5e2034429c836cca=1582267903; Hm_lpvt_414bd23f4090657a5e2034429c836cca=1582268032",
"Host":
"share.izuiyou.com",
"Origin":
"https://share.izuiyou.com",
"Referer":
url,
"Sec-Fetch-Mode":
"cors",
"Sec-Fetch-Site":
"same-origin",
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"
}
post_url = "https://share.izuiyou.com/api/review/share_review"
play_host = "http://tbvideo.ixiaochuan.cn/"
path = urlparse(url).path
temp = path.split("/")
pid = temp[-2]
rid = temp[-1]
payload = {
"h_av": "3.0",
"h_dt": 9,
"h_nt": 9,
"h_ch": "web_app",
"ua":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36",
"pid": f"{pid}",
"rid": f"{rid}"
}
rep = requests.post(post_url,
data=json.dumps(payload),
headers=headers,
timeout=20)
if rep.status_code == 200:
data = rep.json()
try:
audio_info = data.get("data").get("review").get("audio")
voice_text = audio_info.get("voice_text")
uri = audio_info.get("uri")
org_uri = audio_info.get("org_uri")
except AttributeError:
voice_text = ""
uri = ""
org_uri = ""
if voice_text:
result.text = voice_text
if org_uri:
org_uri = play_host + org_uri
result.audioUrls.append(org_uri)
elif uri:
uri = play_host + uri
result.audioUrls.append(uri)
else:
raise NotFoundException
except errors as e:
result.err = 1
result.msg = e.message
return result()