summaryrefslogtreecommitdiffstats
path: root/bin/get-forum-attachments.py
blob: 4e46befefa9a3794496d8a165816befedff9b809 (plain)
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
#!/usr/bin/env python3

# This file is part of the LibreOffice project.
#
# This Source Code Form is subject to the terms of the Mozilla Public
# License, v. 2.0. If a copy of the MPL was not distributed with this
# file, You can obtain one at http://mozilla.org/MPL/2.0/.

import argparse
import configparser
import hashlib
import magic
import os
import requests
import shutil
import sys
import tempfile

from bs4 import BeautifulSoup
from attachment_mimetypes import mimetypes
from concurrent.futures import ThreadPoolExecutor, as_completed
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry

forums = {
    # https://wiki.documentfoundation.org/Website/Web_Sites_services#Unofficial_and_Related_Pages
    'en': "https://forum.openoffice.org/en/forum",
    'es': "https://forum.openoffice.org/es/forum",
    'fr': "https://forum.openoffice.org/fr/forum",
    'hu': "https://forum.openoffice.org/hu/forum",
    'it': "https://forum.openoffice.org/it/forum",
    'ja': "https://forum.openoffice.org/ja/forum",
    'nl': "https://forum.openoffice.org/nl/forum",
    'pl': "https://forum.openoffice.org/pl/forum",
    'vi': "https://forum.openoffice.org/vi/forum",
    'tr': "https://forum.libreoffice.org.tr",
    'de': "https://www.openoffice-forum.de",
    'de2': "https://www.libreoffice-forum.de",
    'de3': "https://de.openoffice.info",
    # Others
    'mso-en': "https://www.msofficeforums.com",
    'mso-de': "https://www.ms-office-forum.net/forum",
}

def do_login(session, url, configFile):
    config = configparser.ConfigParser()

    config.read(configFile)
    username = config.get('login', 'username')
    password = config.get('login', 'password')
    resp = session.post(url + '/login.php?do=login', {
    'vb_login_username':        username,
    'vb_login_password':        '',
    'vb_login_md5password':     hashlib.md5(password.encode()).hexdigest(),
    'vb_login_md5password_utf': hashlib.md5(password.encode()).hexdigest(),
    'cookieuser': 1,
    'do': 'login',
    's': '',
    'securitytoken': 'guest'
    })

    if resp.status_code != 200:
        return False

    soup = BeautifulSoup(resp.content, 'lxml')
    for p in soup.find_all("p"):
        if 'Thank you for logging in' in p.get_text():
            return True
        elif 'Danke für Ihre Anmeldung' in p.get_text():
            return True

    return False

def get_attachments_from_url(lang, url, pathes):

    print("Checking " + url)

    startIndex = 0

    # Keep the index and resume from there
    indexFile = os.path.join(pathes.outdir, lang + ".index")
    if os.path.isfile(indexFile):
        with open(indexFile) as f:
            startIndex = int(f.readline().rstrip()) + 1
    else:
        if lang == 'hu':
            startIndex = 1300

    session = requests.Session()
    retry = Retry(connect=3, backoff_factor=0.5)
    adapter = HTTPAdapter(max_retries=retry)
    session.mount('http://', adapter)
    session.mount('https://', adapter)

    if lang.startswith("mso"):
        if not do_login(session, url, pathes.config):
            print("Can't log in to " + url)
            return

    invalidCount = 0
    for i in range(startIndex, 999999):
        if lang.startswith("mso"):
            fileUrl = url + "/attachment.php?attachmentid=" + str(i)
        else:
            fileUrl = url + "/download/file.php?id=" + str(i)

        h = session.head(fileUrl)
        header = h.headers
        content_type = header.get('content-type')
        if "html" in content_type:
            # Let's assume this is an invalid file link
            invalidCount += 1

            # Let's assume, if we get 100 invalid files, that there are no more files
            if invalidCount == 100:
                print("No more attachments found in " + url)
                break
        else:
            invalidCount = 0

            r = session.get(fileUrl, allow_redirects=True)
            with tempfile.NamedTemporaryFile() as tmp:
                tmp.write(r.content)
                mimetype = magic.from_file(tmp.name, mime=True)
                if mimetype in mimetypes:
                    suffix = mimetypes[mimetype]
                    suffixDir = os.path.join(pathes.outdir, suffix)
                    try:
                        os.mkdir(suffixDir)
                    except:
                        pass

                    download = os.path.join(suffixDir,
                            "forum-" + lang + '-' + str(i) + '.' + suffix)

                    print("Downloading as " + download)
                    shutil.copy(tmp.name, download)

            # Save the index
            with open(indexFile, 'w') as f:
                f.write(str(i))

if __name__ == '__main__':
    parser = argparse.ArgumentParser()

    parser.add_argument('--outdir', action='store', dest="outdir", required=True)
    parser.add_argument('--config', action="store", dest="config", required=True)

    pathes = parser.parse_args()

    if not os.path.exists(pathes.outdir) or os.path.isfile(pathes.outdir):
        print("Outdir folder doesn't exists")
        sys.exit(1)
    elif not os.path.exists(pathes.config) or not os.path.isfile(pathes.config):
        print("Config file doesn't exists")
        sys.exit(1)

    processes = []
    # 10 at a time seems to work fine
    with ThreadPoolExecutor(max_workers=10) as executor:
        for lang, url in forums.items():
            processes.append(executor.submit(get_attachments_from_url, lang, url, pathes))

    for task in as_completed(processes):
        result = task.result()
        if result:
            print(result)