Changed a lot of things to release on PyPI

LICENSE

@@ -1,26 +1,21 @@
-Copyright (c) 2016, lacsap-
-All rights reserved.
+The MIT License (MIT)
 
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
+Copyright (c) 2016 lacsap
 
-1. Redistributions of source code must retain the above copyright notice, this
-   list of conditions and the following disclaimer.
-2. Redistributions in binary form must reproduce the above copyright notice,
-   this list of conditions and the following disclaimer in the documentation
-   and/or other materials provided with the distribution.
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
 
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
-ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
-ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
-(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
-LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
-ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
 
-The views and conclusions contained in the software and documentation are those
-of the authors and should not be interpreted as representing official policies,
-either expressed or implied, of the FreeBSD Project.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

MANIFEST.in

@@ -0,0 +1 @@
+include README.md

README.md

@@ -3,10 +3,9 @@
 4scanner search 4chan's thread for matching keywords then download all images
 to disk
 
-## Requirements
-- requests
+## Installing
 
-To install all requirements: ``` pip install -r requirement.txt ```
+``` pip install 4scanner ```
 
 ## How to
 
@@ -16,7 +15,7 @@ folder you want, the board(s) you want to search and the keywords.
 
 After your json file is done you can start 4scanner with:
 
-``` 4scanner.py file.json ```
+``` 4scanner file.json ```
 
 it will search all threads for the keywords defined in your json file and
 download all images/webms from threads where a keyword is found.
@@ -49,12 +48,11 @@ Here is an example of what the JSON file should look like:
 - /f/ - Flash is not supported (yet?)
 - the keywords search is case insentitive
 
-## download.py
+## 4downloader
 
-download.py is the script used to download the threads found with the keywords.
-You can use this this script alone to download a single thread by doing:
-
-``` download.py http://boards.4chan.org/b/thread/373687492 ```
+4downloader is also installed with 4scanner and can be use to download
+a single thread like this:
+``` 4downloader http://boards.4chan.org/b/thread/373687492 ```
 
 It will download all images until the thread die.
 

bin/4downloader

@@ -0,0 +1,43 @@
+#!/usr/bin/env python3
+
+import argparse
+import os
+import scanner
+from scanner import download
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('thread', help='url of the thread')
+    parser.add_argument('folder', nargs='?',
+                        help='Change the folder name where images are downloaded')
+    parser.add_argument("-q", "--quiet", action='store_true', help="quiet")
+    parser.add_argument("-o", "--output", help="Specify output folder")
+    args = parser.parse_args()
+
+    print(args.thread)
+
+    quiet = False
+    if args.quiet:
+        quiet = True
+
+    if args.folder is not None:
+        folder = ''.join(args.folder)
+    else:
+        folder = ''.join(args.thread).split('/')[5].split('#')[0]
+
+    if args.output is not None:
+        output = args.output
+        if not os.path.exists(output):
+            print("{0} Does not exist.".format(output))
+            exit(1)
+    else:
+        output = os.getcwd()
+
+    download.download_thread(args.thread, output, folder, quiet)
+
+
+if __name__ == '__main__':
+    try:
+        main()
+    except KeyboardInterrupt:
+        pass

bin/4scanner

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+
+import argparse
+import os
+import scanner
+from scanner import scanner
+import time
+
+
+def main():
+    # Arguments parsing and validation
+    parser = argparse.ArgumentParser()
+    parser.add_argument("keywords_file",
+                        help="file with the keywords to search for")
+    parser.add_argument("-o", "--output", help="Specify output folder")
+    args = parser.parse_args()
+
+    # Checking keywords file
+    if not os.path.isfile(args.keywords_file):
+            print("Keywords file does not exist...")
+            exit(1)
+
+    if args.output:
+        output = args.output
+        if not os.path.exists(output):
+            print("{0} Does not exist.".format(output))
+            exit(1)
+    else:
+        output = os.getcwd()
+
+    log_file = "downloaded-{0}.txt".format(time.strftime('%d%m%Y_%H%M'))
+
+    scanner.scan(args.keywords_file, output, log_file)
+
+
+if __name__ == '__main__':
+    try:
+            main()
+    except KeyboardInterrupt:
+        pass

download.py → scanner/download.py

@@ -10,37 +10,6 @@
 import requests
 
 
-def main():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('thread', help='url of the thread')
-    parser.add_argument('folder', nargs='?',
-                        help='Change the folder name where images are downloaded')
-    parser.add_argument("-q", "--quiet", action='store_true', help="quiet")
-    parser.add_argument("-o", "--output", help="Specify output folder")
-    args = parser.parse_args()
-
-    print(args.thread)
-
-    quiet = False
-    if args.quiet:
-        quiet = True
-
-    if args.folder is not None:
-        folder = ''.join(args.folder)
-    else:
-        folder = ''.join(args.thread).split('/')[5].split('#')[0]
-
-    if args.output is not None:
-        output = args.output
-        if not os.path.exists(output):
-            print("{0} Does not exist.".format(output))
-            exit(1)
-    else:
-        output = os.path.dirname(os.path.realpath(__file__))
-
-    download_thread(args.thread, output, folder, quiet)
-
-
 def load(url):
     response = requests.get(url)
     response.raise_for_status()
@@ -68,9 +37,3 @@ def download_thread(thread, output_folder, folder, is_quiet):
             if not is_quiet:
                 print('thread 404\'d')
             exit(0)
-
-if __name__ == '__main__':
-    try:
-        main()
-    except KeyboardInterrupt:
-        pass