Merge pull request #17 from grantat/local-quote

Adds quoting to local version. Updates Readme with examples for disabling module and docker with environment variables. Related to #15.

README.md

@@ -49,10 +49,36 @@ To run it as a local script:
 $ ./main.py -l search {URI-R}
 ```
 
-The backlinks calculation is costly to your computers, so it is recommended to turn it off:
+### Environment variables
+
+Carbon Date provides the option of passing in environment variables for both the Bing and Bitly services.
+For Bitly, the environment key is `CD_Bitly_token`. For Bing, the environment key is `CD_Bing_key`.
+Environment variables can be passed into docker using the `-e` or `--env` arguments before executing the Carbon Date application like so:
+
+```
+$ docker run -e "CD_Bitly_token=foo" -e "CD_Bing_key=bar" -it --rm oduwsdl/carbondate ./main.py -l search http://www.cs.odu.edu/
+```
+
+### Disabling modules
+
+CarbonDate provides the option of preventing searching for specified modules in the local version.
+For example, if a user wants to disable backlinks and google modules the user can add the `-e` argument after a URI-R is specified like so:
+
+```
+./main.py -l search "https://www.cs.odu.edu/" -e cdGetBacklinks cdGetGoogle
+```
+
+A complete list of all the modules a user can disable is as follows:
 
 ```
-$ ./main.py -l search {URI-R} -e cdGetBacklinks
+cdGetPubdate
+cdGetArchives
+cdGetBing
+cdGetBitly
+cdGetTwitter
+cdGetBacklinks
+cdGetGoogle
+cdGetLastModified
 ```
 
 ## How to add your module

main.py

@@ -3,6 +3,7 @@
 import argparse
 import os
 import sys
+import shlex
 
 logo = ('''
  _____       ___   _____    _____   _____   __   _   _____       ___   _____   _____
@@ -36,6 +37,9 @@ def parserinit():
     if args.server:
         os.system('./server.py')
     elif args.local:
-        os.system('./local.py %s' % ' '.join(sys.argv[2:]))
+        arg_str = ""
+        for a in sys.argv[2:]:
+            arg_str += (' ' + shlex.quote(a))
+        os.system('./local.py%s' % (arg_str))
     elif args.lh:
         os.system('./local.py -h')

modules/cdGetGoogle.py

@@ -6,6 +6,7 @@
 from .cdGetLowest import getLowest, validateDate
 from random import randint
 import logging
+import urllib.parse
 
 moduleTag = 'google.com'
 
@@ -135,6 +136,7 @@ def getGoogle(url, outputArray, indexOfOutputArray, verbose=False, **kwargs):
 
     # Caution google blocks bots which do not play nice
     # return ''
+    url = urllib.parse.quote(url, safe='')
     query = ('https://www.google.com/search?hl=en&tbo=d&tbs=qdr:y15'
              '&q=inurl:' + url + '&oq=inurl:' + url)