summaryrefslogtreecommitdiffstats
path: root/comedyGenerator
blob: 763ea6fec4fe44cb75c35a7101a1aae20e08b34f (plain) (blame)
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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
#!/usr/bin/python3
import requests
import urllib.request
import os
import argparse
import time
import configparser
from multiprocessing import Pool
import xdg
import configparser
import os 

API_URL = "https://ifunny.co/api/v1/feeds/tags/"

class Video:
    def __init__(self, url, name):
        self.url = url
        self.name = name

config = configparser.ConfigParser()
configdir = str(xdg.XDG_CONFIG_HOME)
config.read(configdir + "/comedyGenerator")

parser = argparse.ArgumentParser(add_help=True, formatter_class=argparse.RawTextHelpFormatter)

parser.add_argument('--verbose', '-v',
        default=False,
        action='store_true',
        dest='verbose',
        help='Enables verbose output'
        )

parser.add_argument('--amount','-a',
        default=int(config['DEFAULT']['amount']),
        dest='amount',
        action="store",
        help="the amount of funnies you'd like to download per tag",
        type=int
        )

parser.add_argument('--output','-o',
        dest=None,
        action="store",
        help="the output directory of the funnies",
        type=str
        )

parser.add_argument('--log','-l',
        default=config['DEFAULT']['log'],
        dest='log',
        action="store",
        help="the output directory of the log file for your funnies. STDOUT if you wish for standard output.",
        type=str
        )

parser.add_argument('--jobs','-j',
        default=int(config['DEFAULT']['jobs']),
        dest='jobs',
        action="store",
        help="how many jobs you'd like to use while downloading",
        type=int
        )

parser.add_argument('--no-download', '--nd',
        dest='noDownload',
        action="store_true",
        help="If you would like to actually download the funnies or not",
        )

parser.add_argument('--type','-t',
        default=str(config['DEFAULT']['type']),
        dest='type',
        action="store",
        help=
        '''
The type of content that will be extracted 
The following arguments are valid (case insensitive):
Video
Gifs
        ''',
        type=str
        )

parser.add_argument('tags',
        nargs='+',
        type=str,
        help='Provides tags to be check for funny downloading'
        )

args = parser.parse_args()

contentFilter = "video"

if args.output == None:
    if args.verbose:
        print("Recalibtrating output location")
    if args.type.lower() == "video" or args.type.lower() == "videos":
        args.output = config['Videos']['output']
    elif args.type.lower() == "gifs" or args.type.lower() == "gif":
        args.output = config['Gifs']['output']

if args.type.lower() == "video" or args.type.lower() == "videos":
    contentFilter = "video"
elif args.type.lower() == "gifs" or args.type.lower() == "gif":
    contentFilter = "gif"

if args.verbose:
    print("Current output location: " + str(args.output))
    print("Current filter: " + contentFilter)


#string comparision so I don't need two vars; bloat kills bloat
logging = False
if not args.log == "False":
    logging = True
    if args.log == "STDOUT":
        logFile = "STDOUT"
    else:
        logFile = open(args.log, "a")
    tmpLog = []
    if args.verbose:
        print("We're going to be logging!")
        print("Logging Path: " + args.log)

headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; rv:91.0) Gecko/20100101 Firefox/91.0",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
        "Accept-Language": "en-US,en;q=0.5",
        "DNT": "1",
        "Connection": "keep-alive",
        "Upgrade-Insecure-Requests": "1",
        "Sec-Fetch-Dest": "document",
        "Sec-Fetch-Mode": "navigate",
        "Sec-Fetch-Site": "cross-site",
        "Cache-Control": "max-age=0"
        }

for tags in args.tags:
        videos = []
        print("Downloading Tag: " + tags)
        headers = {
                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; rv:91.0) Gecko/20100101 Firefox/91.0",
                "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
                "Accept-Language": "en-US,en;q=0.5",
                "DNT": "1",
                "Connection": "keep-alive",
                "Upgrade-Insecure-Requests": "1",
                "Sec-Fetch-Dest": "document",
                "Sec-Fetch-Mode": "navigate",
                "Sec-Fetch-Site": "cross-site",
                "Cache-Control": "max-age=0"
            }
        
        for tries in range(100):
            try:
                master = requests.get('https://ifunny.co/', headers=headers)
            except:
                if tries < 100 - 1:
                    print("Rate Limited! Sleeping for " + str(tries*1.5) + " seconds!")
                    time.sleep(tries*1.5)
                    continue
            break
        combineHeader = (dict(master.headers)|headers)
        requestHeader = {
                "User-Agent":combineHeader['User-Agent'],
                "Content-Type":combineHeader['Content-Type'],
                "x-requested-with": "fetch",
                "x-csrf-token": combineHeader['Set-Cookie'].split(';')[0].split('=')[1],
                "set-cookies":combineHeader['Set-Cookie'],
                "access-control-allow-headers":combineHeader['access-control-allow-headers']
                }
        requestCookies = {
                "CID" : combineHeader['Set-Cookie'].split(';')[3].split('=')[2],
                "sound" : "off",
                "viewMode" : "list",
                "x-csrf-token": combineHeader['Set-Cookie'].split(';')[0].split('=')[1]
                }
        for tries in range(100):
            try:
                tagPage = requests.get(API_URL + tags + "?filter=" + contentFilter, headers=requestHeader, cookies=requestCookies)
                if args.verbose:
                    print("Got Webpage!")
            except:
                if tries < 100 - 1:
                    print("Rate Limited! Sleeping for " + str(tries*1.5) + " seconds!")
                    time.sleep(tries*1.5)
                    continue
            break

        JSONDump = tagPage.json()

        while len(videos) < args.amount and len(JSONDump['items']) > 0:
            print("Currently have " + str(len(videos)) + " " + contentFilter + " out of " + str(args.amount) + " (" + str((len(videos)/args.amount)*100) + "%)")
            for item in range(len(JSONDump['items'])):
                videos.append( Video(JSONDump['items'][item]['url'], JSONDump['items'][item]['title']) )
            for tries in range(100):
                try:
                    tagPage = requests.get(API_URL + tags + "?filter=" + contentFilter + "&next=" + JSONDump['pagination']['next'], headers=requestHeader, cookies=requestCookies)
                    JSONDump = tagPage.json()
                    if args.verbose:
                        print("Got New Tag Page!")
                    break
                except:
                    if tries < 100 - 1:
                        print("Rate Limited! Sleeping for " + str(tries*1.5) + " seconds!")
                        time.sleep(tries*1.5)
                        continue
        if len(videos) > args.amount:
            videos = videos[:args.amount]
            if args.verbose:
                print("Videos list truncated! Its now: " + str(len(videos)) + " units long")

        def download(video, name):
            if args.verbose:
                print("Now running for " + str(video))

            urlsplit = video.split('.')
            if args.verbose:
                print("url split = " + str(urlsplit))
            if len(name) > 200:
                if args.verbose:
                    print("shortening name because its too long")
                name = name[0:200]
            name = name.replace('"', "")
            outputPath = args.output + tags + " - " + name + "." + urlsplit[len(urlsplit)-1]
            if args.verbose:
                print("name read as: " + name)
            if os.path.exists(outputPath):
                print(name + " already exists!")
            else:
                print("saving " + video + " as " + name)
                if args.type.lower() == "video" or args.type.lower() == "videos":
                    os.system("ffmpeg -y -i \"" + video + "\" \"" + outputPath + "\"") 
                elif args.type.lower() == "gifs" or args.type.lower() == "gif":
                    urllib.request.urlretrieve(video, outputPath)
                if args.verbose:
                    print("saving complete!")
        if args.jobs > 1 and args.noDownload == False:
            pool = Pool(args.jobs)
            for video in videos:
                pool.apply_async(download, (video.url, video.name,))
            pool.close()
            pool.join()
        elif args.noDownload == False:
            for video in videos:
                download(video.url, video.name)
        
        if logging and args.noDownload == False:
            for video in videos:
                logName = video.url
                logPath = args.output + logName
                if args.verbose:
                    print("Writing " + logPath + " to log file")
                logFile.write(logPath + "\n")
        elif logging:
            for video in videos:
                logName = video.url
                if args.verbose:
                    print("Writing " + logName + " to log file")
                logFile.write(logName + "\n")
if logging:
    logFile.close()

#This program is free software: you can redistribute it and/or modify
#it under the terms of the GNU Affero General Public License version 3 as published by
#the Free Software Foundation.
#
#This program is distributed in the hope that it will be useful,
#but WITHOUT ANY WARRANTY; without even the implied warranty of
#MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#GNU Affero General Public License for more details.
#
#You should have received a copy of the GNU Affero General Public License
#along with this program.  If not, see <https://www.gnu.org/licenses/>.