diff --git a/README b/README
deleted file mode 100644
index f26ef74..0000000
--- a/README
+++ /dev/null
@@ -1,13 +0,0 @@
-This is quick weekend hack made to access Wikipedia from command line.
-
-
-Its written in python.To compile it just run 'python cliwiki.py'(without quotes) from your terminal and then enter the search title to get Wikipedia page on your terminal!
-
-
-It can also be given one of following 3 command line arguments.
-
-1)potd
-2)featured
-3)onthisday
-
-this is just a quick hack and there's lot of crappy code in it.So please feel free to fork and send pull request if u want to improve it.
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..266d4d9
--- /dev/null
+++ b/README.md
@@ -0,0 +1,24 @@
+Wikipedia CLI
+=========
+
+Command line interface to access wikipedia pages.
+
+This version is a fork of [AnirudhBhat](https://github.com/AnirudhBhat)'s and now run on python 3.
+
+
+## Usage
+~~~bash
+$ ./cliwiki.py -h
+usage: cliwiki.py [-h] [-d | -f | -p] search
+
+Access Wikipedia from Command Line
+
+positional arguments:
+ search Page to search for on Wikipedia
+
+optional arguments:
+ -h, --help show this help message and exit
+ -d, --today Display URLs for the "On this day" pages
+ -f, --featured Display the featured articles URLs
+ -p, --picture Display URLs for the "Picture of the day" pages
+~~~
\ No newline at end of file
diff --git a/climovie.py b/climovie.py
deleted file mode 100755
index 6aca2aa..0000000
--- a/climovie.py
+++ /dev/null
@@ -1,45 +0,0 @@
-#! /usr/bin/env python
-
-from __future__ import print_function
-import urllib2
-import json
-
-API_KEY = "c5b633xj3ats73tmf9cez333"
-
-base_url = "http://api.rottentomatoes.com/api/public/v1.0"
-
-
-type = "/lists/movies/box_office.lson?apikey="
-
-
-url = base_url + type + API_KEY
-
-result = json.load(urllib2.urlopen(url))
-
-k=0
-z=0
-
-for i in result["movies"]:
- print(i["title"])
- print("SYNOPSIS",end="\n")
- print(i["synopsis"],end="\n")
- print("TRAILER",end="\n")
- print(i["links"]["clips"],end="\n")
- print("CASTS",end="\n")
- for j in result["movies"][k]["abridged_cast"]:
- print(j["name"])
- print(j["characters"],end="\n\n\n")
- #for a in result["movies"]:
- print("CRITICS_RATING:",end=" ")
- print(result["movies"][z]["ratings"]["critics_rating"])
- print("CRITICS_SCORE:",end=" ")
- print(result["movies"][z]["ratings"]["critics_score"])
- print("AUDIENCE_RATING:",end=" ")
- print(result["movies"][z]["ratings"]["audience_rating"])
- print("AUDIENCE_SCORE:",end=" ")
- print(result["movies"][z]["ratings"]["audience_score"],end="\n\n\n")
- print("\t-----------------------------------------------------------")
- #print(i["abridged_cast"][j]["name"])
- #print(i["abridged_cast"][j]["characters"],end="\n\n\n")
- z=z+1
- k=k+1
diff --git a/cliwiki.py b/cliwiki.py
old mode 100644
new mode 100755
index b87b854..f67645b
--- a/cliwiki.py
+++ b/cliwiki.py
@@ -1,180 +1,220 @@
-#! /usr/bin/env python
+#! /usr/bin/env python3
+
+""" CLI to access wikipedia informations """
-from __future__ import print_function
import json
-import urllib2
-import sys
+import urllib.request
import re
+import argparse
+# **** Global Variables ****
+BASE_URL = "http://en.wikipedia.org/w/api.php?"
+ACTION = "action=query"
+FORMAT = "&format=json"
+TITLES = "&titles="
-KEY = 0
-
-base_url = "http://en.wikipedia.org/w/api.php?"
-action = "action=query"
+# **** Functions ****
-Format = "&format=json"
+def wiki_search():
+ """ Search function """
+ prop = "&prop=extracts"
+ plaintext = "&explaintext"
+ section_format = "&exsectionformat=plain"
-titles="&titles="
+ try:
+ url = (BASE_URL + ACTION + TITLES
+ + prop + plaintext + section_format + FORMAT)
+ # open url, read content (bytes), convert in string via decode()
+ result = json.loads(urllib.request.urlopen(url).read().decode('utf-8'))
+ key = list(result['query']['pages'].keys())[0][0:]
+ print(result['query']['pages'][key]['extract'])
-def get_title():
- title = raw_input('enter the title you want to search\n')
- title = title.replace(' ','_')
- global titles
- titles = titles + title
+ except KeyError:
+ print('No wikipedia page for that title. '
+ 'Wikipedia search titles are case sensitive.')
def url_and_displaytitle():
- print('\ntitle and url for this wikipedia site',end="\n")
- global base_url
- global action
- global titles
- global Format
- prop = "&prop=info"
- inprop = "&inprop=url|displaytitle"
- url = base_url + action + titles + prop + inprop + Format
- result = json.load(urllib2.urlopen(url))
- key = result['query']['pages'].keys()
- global KEY
- KEY = (key[0][:])
- print(result['query']['pages'][str(KEY)]['title'])
- print(result['query']['pages'][str(KEY)]['fullurl'])
- print('\t-------------------\t')
-
+ """ Display URL and Title for the page """
-def interesting_links():
- print('\nyou may also be interested in the following links',end="\n")
- global base_url
- global Format
- global action
- global titles
- prop = "&prop=extlinks"
- try:
- url = base_url + action + titles + prop + Format
- result =json.load(urllib2.urlopen(url))
- key = result['query']['pages'].keys()
- key = key[0][0:]
- j = 0
- offset = result['query-continue']['extlinks']['eloffset']
- while j < offset:
- print(result['query']['pages'][str(key)]['extlinks'][j])
- j=j+1
- except:
- print('sorry,couldn\'t find any links')
+ print('\n\nTitle and url for this Wikipedia page: \n')
+ prop_inprop = "&prop=info&inprop=url|displaytitle"
+ url = BASE_URL + ACTION + TITLES + prop_inprop + FORMAT
+ # open url, read content (bytes), convert in string via decode()
+ result = json.loads(urllib.request.urlopen(url).read().decode('utf-8'))
-#def interwiki_links():
- # print('inter wiki links found for this search',end="\n")
- # base_url
- # action
- # titles
- # prop = "&prop=iwlinks"
- # url = base_url + action + titles + prop
- # print(url)
- # result = urllib2.urlopen(url)
- # for i in result:
- # print(i)
+ # In python 3 dict_keys are not indexable, so we need to use list()
+ key = list(result['query']['pages'].keys())[0][:]
+ print('\t'+result['query']['pages'][key]['title'])
+ print('\t'+result['query']['pages'][key]['fullurl'])
+ print('\n\t-------------------\t')
-def wiki_search():
- global base_url
- global action
- global titles
- global Format
- prop = "&prop=extracts"
- plaintext = "&explaintext"
- section_format = "&exsectionformat=plain"
+def interesting_links():
+
+ """Fonction displaying related links => Interest on the CLI ?"""
+
+ print('\nYou may also be interested in the following links: \n')
+
+ prop = "&prop=extlinks"
+
try:
- url = base_url + action + titles + prop + plaintext + section_format + Format
- result = json.load(urllib2.urlopen(url))
- key = result['query']['pages'].keys()
- key = key[0][0:]
- print(result['query']['pages'][str(key)]['extract'],end="\n")
- except:
- print('oops!,no wikipedia page for that title.Wikipedia search titles are case Sensitive...')
-
+ url = BASE_URL + ACTION + TITLES + prop + FORMAT
+ # open url, read content (bytes), convert in string via decode()
+ result = json.loads(urllib.request.urlopen(url).read().decode('utf-8'))
+
+ key = list(result['query']['pages'].keys())[0][0:]
+
+ offset = result['query-continue']['extlinks']['eloffset']
+
+ for j in range(0, offset):
+
+ # ['*'] => elements of ....[j] are dict, and their keys are '*'
+ print('\t'+result['query']['pages'][key]['extlinks'][j]['*'])
+
+ except KeyError:
+ print("Sorry, we couldn't find any links.")
def images():
- print('\nall images related to this search',end="\n")
+ """ Get images urls """
+
image_url = "http://en.wikipedia.org/wiki/"
- global base_url
- global Format
- global action
- global titles
prop = "&prop=images"
- url = base_url + action + titles + prop + Format
- result = json.load(urllib2.urlopen(url))
- key = result['query']['pages'].keys()
- key = key[0][0:]
+ url = BASE_URL + ACTION + TITLES + prop + FORMAT
+
+ print('\nAll images related to this search : \n')
+
+ # open url, read content (bytes), convert in string via decode()
+ result = json.loads(urllib.request.urlopen(url).read().decode('utf-8'))
+
+ key = list(result['query']['pages'].keys())[0][0:]
+
try:
- i = 1
- while(i):
- Image = str(result['query']['pages'][str(key)]['images'][i]['title'])
- image = image_url + Image.replace(' ','_')
- print(image)
- i=i+1
- except:
- print('\t------------------\t',end="\n")
- pass
-
+ for i in range(1, len(result['query']['pages'][key]['images'])):
+ image = result['query']['pages'][key]['images'][i]['title']
+ image = image_url + image.replace(' ', '_')
+ print('\t'+image)
+ print('\n\t------------------\t')
+ except KeyError:
+ print('\n\t------------------\t')
-def featured_feed():
- global base_url
- Format = "&format=json"
- action = "&action=featuredfeed"
- try:
- feed = "&feed=" + str(sys.argv[1])
- url = base_url + action + feed + Format
- print(url)
- result = urllib2.urlopen(url).read()
- res1 = re.compile('(.*)')
- res2 = re.compile('(.*)en')
- Result1 = re.findall(res1,result)
- Result2 = re.findall(res2,result)
- for i in enumerate(zip(Result1,Result2)):
- print(i)
- except:
- print('error!')
-
-
+def featured_feed(feed):
+ """Featured Feed"""
+
+ url = BASE_URL + "&action=featuredfeed" + "&feed=" + feed + FORMAT
+
+ result = urllib.request.urlopen(url).read().decode('utf-8')
+
+ re_title = re.compile('(.*)')
+ re_links = re.compile('(.*)en')
+
+ result1 = re.findall(re_title, result)
+ result2 = re.findall(re_links, result)
+
+ print('\n')
+
+ for desc, url in zip(result1, result2):
+ print(desc + ':\t ' + url)
+
+
+
+
+def interwiki_links():
+ """ Inter wiki links """
+
+ print('Inter wiki links found for this search: ')
+
+ url = BASE_URL + ACTION + TITLES + "&prop=iwlinks"+ FORMAT
+ print(url)
+ # TODO: parse the json, match it with a dict containing
+ # url to append depending on the key returned in the url,
+ # and then only show the resulting urls
+
+ # result = urllib.request.urlopen(url).read().decode('utf-8')
+
+ # for i in reslut:
+ # print(i)
+
+
+
+def main():
+ """ Main function """
+
+ # Gestion des paramètres
+ parser = argparse.ArgumentParser(description =
+ "Access Wikipedia from Command Line")
+
+ parser.add_argument('search', help = "Page to search for on Wikipedia")
+
+ group = parser.add_mutually_exclusive_group()
+
+ group.add_argument('-d', '--today',
+ action = 'store_const',
+ const = 'onthisday',
+ help='Display URLs for the "On this day" pages')
+
+ group.add_argument('-f', '--featured',
+ action = 'store_const',
+ const = 'featured',
+ help = 'Display the featured articles URLs')
+
+ group.add_argument('-p', '--picture',
+ action = 'store_const',
+ const = 'potd',
+ help='Display URLs for the "Picture of the day" pages')
+
+ args = parser.parse_args()
+
+ try:
+ if args.search :
+ global TITLES
+ TITLES += args.search.replace(' ','_')
+ wiki_search()
+ url_and_displaytitle()
+ images()
+ interesting_links()
+ # interwiki_links()
-if len(sys.argv) < 2:
- get_title()
- wiki_search()
- url_and_displaytitle()
- images()
- #interwiki_links()
- interesting_links()
-else:
- featured_feed()
+ elif args.featured:
+ featured_feed(args.featured)
+ elif args.picture:
+ featured_feed(args.picture)
+ elif args.today:
+ featured_feed(args.today)
+ except KeyboardInterrupt:
+ print('\n\n Program interrupted')
+if __name__ == "__main__":
+ main()