Mercurial > codedump

annotate channeldownloader.py @ 118:eac6dae753ca

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
*: major cleanup committer: GitHub <noreply@github.com>
author Paper <37962225+mrpapersonic@users.noreply.github.com>
date Fri, 03 Mar 2023 22:51:28 +0000
parents 80bd4a99ea00
children 196cf2e3d96e
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
67
9636d5dee08c [channeldownloader.py] Python 2.7 compatibility
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 61
diff changeset
1 #!/usr/bin/env python3
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
2 """
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
3 Usage:
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
4 channeldownloader.py <url>... (--database <file>)
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
5 [--output <folder>]
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
6 [--proxy <proxy>]
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
7 channeldownloader.py -h | --help
67
9636d5dee08c [channeldownloader.py] Python 2.7 compatibility
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 61
diff changeset
8
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
9 Arguments:
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
10 <url> YouTube channel URL to download from
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
11
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
12 Options:
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
13 -h --help Show this screen
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
14 -o --output <folder> Output folder, relative to the current directory
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
15 [default: .]
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
16 -d --database <file> HTTP or HTTPS proxy (SOCKS5 with PySocks)
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
17 """
67
9636d5dee08c [channeldownloader.py] Python 2.7 compatibility
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 61
diff changeset
18 from __future__ import print_function
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
19 import docopt
67
9636d5dee08c [channeldownloader.py] Python 2.7 compatibility
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 61
diff changeset
20 import internetarchive
9636d5dee08c [channeldownloader.py] Python 2.7 compatibility
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 61
diff changeset
21 try:
9636d5dee08c [channeldownloader.py] Python 2.7 compatibility
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 61
diff changeset
22 import orjson as json
9636d5dee08c [channeldownloader.py] Python 2.7 compatibility
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 61
diff changeset
23 except ImportError:
9636d5dee08c [channeldownloader.py] Python 2.7 compatibility
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 61
diff changeset
24 import json
47
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
25 import os
59
a3927b2ec6e6 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 58
diff changeset
26 import re
68
a43ed076b28f [channeldownloader.py] Implement HTTPError to circumvent Python 2 weirdness
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 67
diff changeset
27 import time
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
28 import urllib.request
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
29 import requests # need this for ONE (1) exception
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
30 import yt_dlp as youtube_dl
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
31 from urllib.error import HTTPError
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
32 from yt_dlp.utils import sanitize_filename, DownloadError
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
33 from pathlib import Path
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
34 from requests.exceptions import ConnectTimeout
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
35
47
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
36
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
37 class MyLogger(object):
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
38 def debug(self, msg):
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
39 pass
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
40
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
41 def warning(self, msg):
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
42 pass
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
43
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
44 def error(self, msg):
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
45 print(" " + msg)
47
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
46 pass
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
47
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
48
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
49 def ytdl_hook(d) -> None:
47
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
50 if d["status"] == "finished":
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
51 print(" downloaded %s: 100%% " % (os.path.basename(d["filename"])))
47
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
52 if d["status"] == "downloading":
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
53 print(" downloading %s: %s\r" % (os.path.basename(d["filename"]),
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
54 d["_percent_str"]), end="")
47
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
55 if d["status"] == "error":
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
56 print("\n an error occurred downloading %s!"
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
57 % (os.path.basename(d["filename"])))
47
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
58
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
59
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
60 def load_split_files(path: str) -> dict:
61
c615532e6572 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 60
diff changeset
61 if os.path.isdir(path):
c615532e6572 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 60
diff changeset
62 result = {"videos": []}
69
63e6bc911606 Use regex instead of weirdness to filter archive.org names
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 68
diff changeset
63 for fi in os.listdir(path):
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
64 for f in re.findall(r"vids[0-9\-]+?\.json", fi):
69
63e6bc911606 Use regex instead of weirdness to filter archive.org names
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 68
diff changeset
65 with open(path + "/" + f, "r", encoding="utf-8") as infile:
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
66 jsonnn = json.loads(infile.read())
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
67 result["videos"].extend(jsonnn)
61
c615532e6572 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 60
diff changeset
68 return result
c615532e6572 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 60
diff changeset
69 else:
67
9636d5dee08c [channeldownloader.py] Python 2.7 compatibility
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 61
diff changeset
70 return json.loads(open(path, "r", encoding="utf-8").read())
61
c615532e6572 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 60
diff changeset
71
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
72
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
73 def reporthook(count: int, block_size: int, total_size: int) -> None:
68
a43ed076b28f [channeldownloader.py] Implement HTTPError to circumvent Python 2 weirdness
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 67
diff changeset
74 global start_time
a43ed076b28f [channeldownloader.py] Implement HTTPError to circumvent Python 2 weirdness
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 67
diff changeset
75 if count == 0:
a43ed076b28f [channeldownloader.py] Implement HTTPError to circumvent Python 2 weirdness
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 67
diff changeset
76 start_time = time.time()
a43ed076b28f [channeldownloader.py] Implement HTTPError to circumvent Python 2 weirdness
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 67
diff changeset
77 return
a43ed076b28f [channeldownloader.py] Implement HTTPError to circumvent Python 2 weirdness
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 67
diff changeset
78 percent = int(count * block_size * 100 / total_size)
a43ed076b28f [channeldownloader.py] Implement HTTPError to circumvent Python 2 weirdness
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 67
diff changeset
79 print(" downloading %d%% \r" % (percent), end="")
a43ed076b28f [channeldownloader.py] Implement HTTPError to circumvent Python 2 weirdness
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 67
diff changeset
80
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
81
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
82 def write_metadata(i: dict, basename: str) -> None:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
83 if not os.path.exists(basename + ".info.json"):
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
84 with open(basename + ".info.json", "w", encoding="utf-8") as jsonfile:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
85 try:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
86 jsonfile.write(json.dumps(i).decode("utf-8"))
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
87 except AttributeError:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
88 jsonfile.write(json.dumps(i))
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
89 print(" saved %s" % os.path.basename(jsonfile.name))
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
90 if not os.path.exists(basename + ".description"):
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
91 with open(basename + ".description", "w",
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
92 encoding="utf-8") as descfile:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
93 descfile.write(i["description"])
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
94 print(" saved %s" % os.path.basename(descfile.name))
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
95
47
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
96
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
97 ytdl_opts = {
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
98 "retries": 100,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
99 "nooverwrites": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
100 "call_home": False,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
101 "quiet": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
102 "writeinfojson": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
103 "writedescription": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
104 "writethumbnail": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
105 "writeannotations": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
106 "writesubtitles": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
107 "allsubtitles": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
108 "addmetadata": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
109 "continuedl": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
110 "embedthumbnail": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
111 "format": "bestvideo+bestaudio/best",
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
112 "restrictfilenames": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
113 "no_warnings": True,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
114 "progress_hooks": [ytdl_hook],
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
115 "logger": MyLogger(),
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
116 "ignoreerrors": False,
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
117 }
00403c09455c Add channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents:
diff changeset
118
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
119
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
120 def wayback_machine_dl(video: dict, basename: str) -> int:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
121 try:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
122 url = ''.join(["https://web.archive.org/web/2oe_/http://wayback-fakeu",
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
123 "rl.archive.org/yt/%s"])
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
124 headers = urllib.request.urlopen(url % video["id"])
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
125 contenttype = headers.getheader("Content-Type")
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
126 if contenttype == "video/webm":
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
127 ext = "webm"
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
128 elif contenttype == "video/mp4":
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
129 ext = "mp4"
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
130 else:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
131 raise HTTPError(url=None, code=None, msg=None,
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
132 hdrs=None, fp=None)
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
133 urllib.request.urlretrieve(url % video["id"], "%s.%s" % (basename, ext),
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
134 reporthook)
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
135 print(" downloaded %s.%s" % (basename, ext))
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
136 return 0
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
137 except TimeoutError:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
138 return 1
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
139 except HTTPError:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
140 print(" video not available on the Wayback Machine!")
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
141 return 0
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
142 except Exception as e:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
143 print(" unknown error downloading video!\n")
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
144 print(e)
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
145 return 0
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
146
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
147 def internet_archive_dl(video: dict, basename: str) -> int:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
148 if internetarchive.get_item("youtube-%s" % video["id"]).exists:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
149 fnames = [f.name for f in internetarchive.get_files(
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
150 "youtube-%s" % video["id"])]
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
151 flist = []
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
152 for fname in range(len(fnames)):
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
153 if re.search(''.join([r"((?:.+?-)?", video["id"],
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
154 r"\.(?:mp4|jpg|webp|mkv|webm|info\\.json|des"
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
155 r"cription|annotations.xml))"]),
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
156 fnames[fname]):
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
157 flist.append(fnames[fname])
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
158 while True:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
159 try:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
160 internetarchive.download("youtube-%s" % video["id"],
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
161 files=flist, verbose=True,
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
162 destdir=output,
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
163 no_directory=True,
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
164 ignore_existing=True,
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
165 retries=9999)
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
166 break
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
167 except ConnectTimeout:
61
c615532e6572 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 60
diff changeset
168 continue
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
169 except Exception:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
170 return 0
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
171 if flist[0][:len(video["id"])] == video["id"]:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
172 for fname in flist:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
173 if os.path.exists("%s/%s" % (output, fname)):
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
174 os.replace("%s/%s" % (output, fname),
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
175 "%s-%s" % (basename.rsplit("-", 1)[0],
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
176 fname))
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
177 return 1
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
178 return 0
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
179
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
180 def main():
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
181 args = docopt.docopt(__doc__)
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
182
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
183 if not os.path.exists(args["--output"]):
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
184 os.mkdir(args["--output"])
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
185
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
186 for i in load_split_files(args["--database"])["videos"]:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
187 uploader = i["uploader_id"] if "uploader_id" in i else None
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
188 for url in args["<url>"]:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
189 channel = url.split("/")[-1]
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
190
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
191 output = "%s/%s" % (args["--output"], channel)
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
192 if not os.path.exists(output):
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
193 os.mkdir(output)
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
194 ytdl_opts["outtmpl"] = output + "/%(title)s-%(id)s.%(ext)s"
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
195
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
196 if uploader == channel:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
197 print("%s:" % i["id"])
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
198 basename = "%s/%s-%s" % (output, sanitize_filename(i["title"],
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
199 restricted=True), i["id"])
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
200 path = Path(output)
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
201 files = list(path.glob("*-%s.mkv" % i["id"]))
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
202 files.extend(list(path.glob("*-%s.mp4" % i["id"])))
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
203 files.extend(list(path.glob("*-%s.webm" % i["id"])))
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
204 if files:
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
205 print(" video already downloaded!")
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
206 write_metadata(i, basename)
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
207 continue
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
208 # this code is *really* ugly... todo a rewrite?
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
209 with youtube_dl.YoutubeDL(ytdl_opts) as ytdl:
114
80bd4a99ea00 Update channeldownloader.py
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 70
diff changeset
210 try:
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
211 ytdl.extract_info("https://youtube.com/watch?v=%s"
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
212 % i["id"])
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
213 continue
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
214 except DownloadError:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
215 print(" video is not available! attempting to find In"
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
216 "ternet Archive pages of it...")
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
217 except Exception as e:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
218 print(" unknown error downloading video!\n")
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
219 print(e)
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
220 if internet_archive_dl(i, basename) == 0: # if we can't download from IA
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
221 print(" video does not have a Internet Archive page! attem"
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
222 "pting to download from the Wayback Machine...")
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
223 while True:
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
224 if wayback_machine_dl(i, basename) == 0: # success
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
225 break
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
226 time.sleep(5)
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
227 continue
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
228 write_metadata(i, basename)
68
a43ed076b28f [channeldownloader.py] Implement HTTPError to circumvent Python 2 weirdness
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 67
diff changeset
229
118
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
230
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
231 if __name__ == "__main__":
eac6dae753ca *: major cleanup
Paper <37962225+mrpapersonic@users.noreply.github.com>
parents: 114
diff changeset
232 main()