Mercurial > codedump

comparison uploadafterdl.py @ 102:eacdf8cc0335

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Update uploadafterdl.py committer: GitHub <noreply@github.com>
author Paper <37962225+mrpapersonic@users.noreply.github.com>
date Mon, 29 Aug 2022 23:21:09 -0400
parents a9776ed0538b
children
comparison
equal deleted inserted replaced
101:a7d2fb3751a0 102:eacdf8cc0335
1 from tubeup.TubeUp import TubeUp 1 from tubeup.TubeUp import TubeUp
2 from yt_dlp.utils import sanitize_filename 2 from yt_dlp.utils import sanitize_filename
3 import glob 3 import glob
4 import json 4 import json
5 import os 5 import os
6 import internetarchive
7
8 seen_ids = []
6 9
7 tu = TubeUp() 10 tu = TubeUp()
8 11
9 for basename in glob.glob('*.info.json'): 12 for basename in glob.glob('*.info.json'):
10 print(basename + " " + str(os.path.getsize(basename))) 13 print(basename + " " + str(os.path.getsize(basename)))
14 sanitize_filename(basename[:-10] + ".webm", restricted=True)]): 17 sanitize_filename(basename[:-10] + ".webm", restricted=True)]):
15 print("no video downloaded") 18 print("no video downloaded")
16 continue 19 continue
17 with open(basename, "r", encoding="utf-8") as jf: 20 with open(basename, "r", encoding="utf-8") as jf:
18 jsons = json.load(jf) 21 jsons = json.load(jf)
19 try: 22 jsons["extractor"] = "youtube" if "extractor" not in jsons else jsons["extractor"]
20 jsons["extractor"] 23 jsons["display_id"] = basename[:-10].split("-")[:-11] if "extractor" not in jsons else jsons["id"]
21 except: 24 jsons["title"] = jsons["fulltitle"] if "extractor" not in jsons else jsons["title"]
22 jsons["extractor"] = "youtube" 25 jsons["webpage_url"] = "https://youtube.com/watch?v=%s" % (jsons["display_id"])
23 try:
24 jsons["display_id"] = jsons["id"]
25 except:
26 jsons["display_id"] = basename[:-10].split("-")[:-11]
27 try:
28 jsons["title"]
29 except:
30 jsons["title"] = jsons["fulltitle"]
31 jsons["webpage_url"] = "https://youtube.com/watch?v=%s" % jsons["display_id"]
32 jsons["extractor_key"] = "Youtube" 26 jsons["extractor_key"] = "Youtube"
33 with open(basename, "w", encoding="utf-8") as jf: 27 with open(basename, "w", encoding="utf-8") as jf:
34 jf.write(json.dumps(jsons)) 28 jf.write(json.dumps(jsons))
35 identifier, meta, item_exists = tu.upload_ia(sanitize_filename(basename[:-10])) 29 if not internetarchive.get_item("%s-%s" % (jsons["extractor"], jsons["display_id"])).exists:
36 print("%s, %s, %s" % (identifier, meta, item_exists)) 30 identifier, meta = tu.upload_ia(sanitize_filename(basename[:-10]))
37 print("uploaded %s" % basename) 31 print("%s, %s" % (identifier, meta))
32 print("uploaded %s" % basename)
33 else:
34 print("skipped %s, item already exists" % basename)