Mercurial > codedump

comparison channeldownloader.py @ 70:eafe13de3f76

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Update channeldownloader.py committer: GitHub <noreply@github.com>
author Paper <37962225+mrpapersonic@users.noreply.github.com>
date Wed, 01 Jun 2022 07:19:02 -0400
parents 63e6bc911606
children 80bd4a99ea00
comparison
equal deleted inserted replaced
69:63e6bc911606 70:eafe13de3f76
72 percent = int(count * block_size * 100 / total_size) 72 percent = int(count * block_size * 100 / total_size)
73 print(" downloading %d%% \r" % (percent), end="") 73 print(" downloading %d%% \r" % (percent), end="")
74 74
75 75
76 parser = argparse.ArgumentParser(description="Downloads (deleted) videos from YTPMV creators") 76 parser = argparse.ArgumentParser(description="Downloads (deleted) videos from YTPMV creators")
77 parser.add_argument("-c", "--channel", help="channel URL", metavar='<url>', required=True) 77 parser.add_argument("-c", "--channel", help="channel URL", metavar="<url>", required=True)
78 parser.add_argument("-d", "--database", help="json database (https://finnrepo.a2hosted.com/YTPMV_Database)", metavar='<path>', required=True) 78 parser.add_argument("-d", "--database", help="json database (https://finnrepo.a2hosted.com/YTPMV_Database)", metavar="<path>", required=True)
79 parser.add_argument("-o", "--output", help="output directory, defaults to the channel ID", metavar='<output>') 79 parser.add_argument("-o", "--output", help="output directory, defaults to the channel ID", metavar="<output>")
80 args = parser.parse_args() 80 args = parser.parse_args()
81 81
82 if args.channel[:8] == "https://" or args.channel[:7] == "http://": 82 if args.channel[:8] == "https://" or args.channel[:7] == "http://":
83 channel = args.channel.split("/")[-1] 83 channel = args.channel.split("/")[-1]
84 else: 84 else:
118 118
119 for i in load_split_files(args.database)["videos"]: 119 for i in load_split_files(args.database)["videos"]:
120 uploader = i["uploader_id"] if "uploader_id" in i else None 120 uploader = i["uploader_id"] if "uploader_id" in i else None
121 if uploader == channel: 121 if uploader == channel:
122 print("%s:" % i["id"]) 122 print("%s:" % i["id"])
123 if os.path.exists(output + "/" + sanitize_filename(i["title"], restricted=True) + "-" + i["id"] + ".info.json"): 123 # :skull:
124 # todo: put this in a function?
125 if any(x in os.listdir(output) for x in [sanitize_filename(i["title"] + "-" + i["id"] + ".mp4", restricted=True),
126 sanitize_filename(i["title"] + "-" + i["id"] + ".mkv", restricted=True),
127 sanitize_filename(i["title"] + "-" + i["id"] + ".webm", restricted=True)]):
124 print(" video already downloaded!") 128 print(" video already downloaded!")
125 continue 129 continue
126 # this code is *really* ugly... todo a rewrite? 130 # this code is *really* ugly... todo a rewrite?
127 with youtube_dl.YoutubeDL(ytdl_opts) as ytdl: 131 with youtube_dl.YoutubeDL(ytdl_opts) as ytdl:
128 try: 132 try:
147 os.rename(output + "/" + fname, output + "/" + sanitize_filename(i["title"], restricted=True) + "-" + fname) 151 os.rename(output + "/" + fname, output + "/" + sanitize_filename(i["title"], restricted=True) + "-" + fname)
148 else: 152 else:
149 print("ID file not found!") 153 print("ID file not found!")
150 else: 154 else:
151 print(" video does not have a Internet Archive page! attempting to download from the Wayback Machine...") 155 print(" video does not have a Internet Archive page! attempting to download from the Wayback Machine...")
152 try: 156 try: # we could use yt-dlp's extractor, but then we would need to craft a fake wayback machine url,
157 # and we wouldn't even know if it worked. so let's continue using our little "hack"
153 headers = compat_urllib.urlopen("https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/%s" % i["id"]) 158 headers = compat_urllib.urlopen("https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/%s" % i["id"])
154 if hasattr(headers.info(), "getheader"): 159 if hasattr(headers.info(), "getheader"):
155 contenttype = headers.info().getheader("Content-Type") 160 contenttype = headers.info().getheader("Content-Type")
156 else: 161 else:
157 contenttype = headers.getheader("Content-Type") 162 contenttype = headers.getheader("Content-Type")
168 except Exception as e: 173 except Exception as e:
169 print(" unknown error downloading video!\n") 174 print(" unknown error downloading video!\n")
170 print(e) 175 print(e)
171 # metadata 176 # metadata
172 with open("%s/%s-%s.info.json" % (output, sanitize_filename(i["title"], restricted=True), i["id"]), "w", encoding="utf-8") as jsonfile: 177 with open("%s/%s-%s.info.json" % (output, sanitize_filename(i["title"], restricted=True), i["id"]), "w", encoding="utf-8") as jsonfile:
173 jsonfile.write(json.dumps(i, ensure_ascii=False).decode('utf-8')) 178 jsonfile.write(json.dumps(i).decode("utf-8"))
174 print(" saved %s" % os.path.basename(jsonfile.name)) 179 print(" saved %s" % os.path.basename(jsonfile.name))
175 180