1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
|
#!/usr/bin/env python3
from html.parser import HTMLParser
from urllib.request import urlopen
class YouTube:
video_type = ""
def mesg(self, msg, t=None):
self.util.mesg(msg, t)
def match_urls(self, str):
r = [
i
for i in str.split()
if "https://youtu.be/" in i
or "https://www.youtube.com/watch?v=" in i
or "https://m.youtube.com/watch?v=" in i
or "https://youtube.com/watch?v=" in i
or "https://www.youtube.com/embed/" in i
or "https://www.youtube-nocookie.com/embed/" in i
or "https://music.youtube.com/watch?v=" in i
or "https://youtube.com/shorts/" in i
or "https://www.youtube.com/shorts/" in i
or "https://www.youtube.com/clip/" in i
or "https://youtube.com/clip/" in i
]
r = list(dict.fromkeys(r))
n = 0
for i in r:
if not i.startswith("http"):
r.pop(n)
n += 1
return r
def is_embed(str):
return str.startswith("https://www.youtube.com/embed/") or str.startswith(
"https://www.youtube-nocookie.com/embed/"
)
def is_ytmusic(str):
return str.startswith("https://music.youtube.com/watch?v=")
def is_ytshorts(str):
return str.startswith("https://youtube.com/shorts/") or str.startswith(
"https://www.youtube.com/shorts/"
)
def is_clip(str):
return str.startswith("https://youtube.com/clip/") or str.startswith(
"https://www.youtube.com/clip/"
)
class parseprop(HTMLParser):
def __init__(self):
print("yt parse init")
HTMLParser.__init__(self)
self.itemprops_list = ["name", "duration", "uploadDate", "interactionCount"]
self.h = {}
if YouTube.video_type == "clip":
self.itemprops_list += ["description"]
print("it is a clip!")
def handle_starttag(self, tag, attrs):
if (tag != "meta" and tag != "link") or (
(
[i for i in attrs if "itemprop" in i] == []
and ("name", "title") not in attrs
)
or (tag == "meta" and ("itemprop", "name") in attrs)
):
return
# print(self,tag,attrs)
for k, v in attrs:
if k == "itemprop":
if v not in self.itemprops_list:
return
x = [v]
if tag == "link" and v == "name":
x = ["channelName"]
elif k == "content":
if attrs[0][1] == "interactionCount":
v = int(v)
x += [v]
elif k == "name" and v == "title":
x = [v]
else:
return
self.h.update({x[0]: x[1]})
# print(x[0],"=",x[1])
def fmt_dur(dur):
h, m, s = 0, 0, 0
m = dur[2:].split("M")
s = int(m[1][:-1])
m = int(m[0])
if m >= 60:
h = m // 60
m = round((m / 60 - h) * 60)
return f"{h}h {m}m {s}s"
elif h == 0 and m == 0 and s == 0:
return "LIVE"
elif m == 0 and s != 0:
return f"{s}s"
elif s == 0:
return f"{m}m"
else:
return f"{m}m {s}s"
def yt(self, url):
# self.util.mesg("dbg hello")
url = url.rstrip("\x01")
self.video_type = (
"clip"
if self.is_clip(url)
else (
"shorts"
if self.is_ytshorts(url)
else (
"music"
if self.is_ytmusic(url)
else "embed" if self.is_embed(url) else "video"
)
)
)
video_type = self.video_type
if video_type == "embed":
videoId = url.split("/")[4]
url = f"https://www.youtube.com/watch?v={videoId}"
elif video_type == "music":
for i in url.split("?")[1].split("&"):
if i[0:2] == "v=":
videoId = i[2:]
url = f"https://www.youtube.com/watch?v={videoId}"
elif video_type == "shorts":
videoId = url.split("?")[0].split("/")[-1]
url = f"https://www.youtube.com/watch?v={videoId}"
p = self.parseprop()
# use premature optimization? it should be SLIGHTLY faster, but can sometimes fail
data = b""
if self.premature_optimization:
url_h = urlopen(url)
# <body> appears on approximately line 21 or 22, so we read 24 lines to be safe (23-25 should be license comment)
# I tried to read byte amounts but it's hard to make sure no invalid utf8 bytes happen due to partial reads
for i in range(24):
data += url_h.readline()
url_h.close()
data = data.decode() # bytes to utf-8
if (
data.find('meta itemprop="duration"') == -1
or data.find('meta itemprop="name"') == -1
): # acts as both fallback for optimization, and in case optimization's turned off
# just read all of the html
data = urlopen(url).read().decode()
# print(f"\x1b[31m my data is: {data}\x1b[0m")
p.feed(data)
if p.h == {}:
irc_string = "[\x0304Youtube\x03] \x0307ERROR:\x0308 got no data from server! \x0315(check your URL for typos!)\x03"
ansi_string = "[\x1b[31mYoutube\x1b[0m] \x1b[33;2mERROR:\x1b[33;1m got no data from server! \x1b[37;2m(check your URL for typos!)\x1b[0m"
print(ansi_string)
return irc_string, True
y = p.h
print(y)
y.update(duration=self.fmt_dur(y["duration"]))
irc_string = f"[\x0303Youtube\x03] \x02{y['title']}\x02 ({y['duration']}) uploaded by \x1d{y['channelName']}\x1d on {y['uploadDate']}, {y['interactionCount']:,} views"
ansi_string = f"[\x1b[32mYoutube\x1b[0m] \x1b[1m{y['title']}\x1b[0m ({y['duration']}) uploaded by \x1b[03m{y['channelName']}\x1b[0m on {y['uploadDate']}, {y['interactionCount']:,} views"
print(ansi_string)
return irc_string, False
if __name__ == "__main__":
import sys
YouTube.premature_optimization = False
YouTube.yt(YouTube, sys.argv[1])
|
