add argument parsing, fix program logic

  * Add argument parsing to extract.py to be able to configure a custom
    output file

  * Update README formatting

  * Fixed program logic in phrases.py, where the program would reference
    the wrong list

  * Lots of general code cleanup and refactoring

diff --git a/README.md b/README.md
index c8e3270b18bd3e9dc97779e16b3d96c728919664..f13e0a169e2909f4458860872644f9c1c6ba82f1 100644 (file)
--- a/README.md
+++ b/README.md
@@ -1,18 +1,18 @@
 # phrases
 # phrases

-Get Latin famous phrases in the terminal
-
-## Source of phrases
-There are currently 2239 phrases in the database, sourced from the Wikipedia page [List of Latin phrases (full)](https://en.wikipedia.org/w/index.php?title=List_of_Latin_phrases_(full)&oldid=986793908)
+Latin famous phrases in the terminal

 
 

+## Source of famous phrases

 Wikipedia contributors, "List of Latin phrases (full)," Wikipedia, The Free Encyclopedia, https://en.wikipedia.org/w/index.php?title=List_of_Latin_phrases_(full)&oldid=986793908. 
 
 Wikipedia contributors, "List of Latin phrases (full)," Wikipedia, The Free Encyclopedia, https://en.wikipedia.org/w/index.php?title=List_of_Latin_phrases_(full)&oldid=986793908. 
 

+There are currently 2239 famous phrases in the database
+

 ## Installation
 `sudo make` to install.
 
 `sudo make uninstall` to uninstall completely.
 
 ### Notes
 ## Installation
 `sudo make` to install.
 
 `sudo make uninstall` to uninstall completely.
 
 ### Notes

-  * If you want to regenerate the phrases.csv file with the `extract.py` script, then you need the BeautifulSoup Python module.
+  * If you want to generate a new phrases.csv file with the `extract.py` script, then you need the BeautifulSoup Python module.

   * Tested and written on Python 3.9.0
 
 ## License
   * Tested and written on Python 3.9.0
 
 ## License

diff --git a/extract.py b/extract.py
index a76fbfbd991d599b789ef062097df750237bddf8..4e6c1f63544e13e9e434718350714ddd080b9382 100755 (executable)
--- a/extract.py
+++ b/extract.py
@@ -2,27 +2,35 @@
 # Extract Latin famous phrases from wikipedia
 # Armaan Bhojwani 2020
 
 # Extract Latin famous phrases from wikipedia
 # Armaan Bhojwani 2020
 

-from bs4 import BeautifulSoup
-import requests
+import argparse
+import sys

 import csv
 import csv

+import requests
+from bs4 import BeautifulSoup

 
 

-def main():
-    url = 'https://en.wikipedia.org/wiki/List_of_Latin_phrases_(full)'
-    response = requests.get(url)
-    html = response.content
-
-    soup = BeautifulSoup(html, "html.parser")
-    list_table = soup.find_all("table", attrs={"class":"wikitable"})
-    with open('phrases.csv', 'w') as f:
+def main(args=sys.argv[1:]):
+    # Argument parsing
+    parser = argparse.ArgumentParser(
+        description="Generate CSV file of Latin famous phrases from Wikipedia.")
+    parser.add_argument("-o", "--output",
+                       default="phrases.csv",
+                       help="set custom output file location")
+    args = parser.parse_args()
+
+    url = ('https://en.wikipedia.org/w/index.php?title=List_of_Latin_phrases_('
+          'full)&oldid=986793908')
+    soup = BeautifulSoup(requests.get(url).content, "html.parser")
+    i = 0 # For the phrase id
+
+    with open(args.output, 'w') as f:

         writer = csv.writer(f, lineterminator="\n")
 
         writer = csv.writer(f, lineterminator="\n")
 

-        i = 0 # For the phrase id
-

         # write header
         headers = ['id', 'Latin', 'English', 'Notes', 'Length']
         writer.writerow(headers)
 
         # iterate through the tables in the page
         # write header
         headers = ['id', 'Latin', 'English', 'Notes', 'Length']
         writer.writerow(headers)
 
         # iterate through the tables in the page

+        list_table = soup.find_all("table", attrs={"class":"wikitable"})

         for table in list_table:
             for row in table.tbody.find_all("tr", recursive=False):
                 cell = row.find_all("td", recursive=False)
         for table in list_table:
             for row in table.tbody.find_all("tr", recursive=False):
                 cell = row.find_all("td", recursive=False)

diff --git a/phrases.py b/phrases.py
index d1d934f2e324d9bf0cabd2b834e22d1103af8f1a..63199d141d996cccc70d160ad3f71438f2909a32 100755 (executable)
--- a/phrases.py
+++ b/phrases.py
@@ -3,52 +3,84 @@
 # Armaan Bhojwani 2020
 
 import argparse
 # Armaan Bhojwani 2020
 
 import argparse

+import csv

 import random
 import sys
 import random
 import sys

-import csv

 
 def main(args=sys.argv[1:]):
     # Argument parsing
 
 def main(args=sys.argv[1:]):
     # Argument parsing

-    parser = argparse.ArgumentParser(description="Latin famous phrases in the terminal.")
-    parser.add_argument("-e", "--english", action='store_true', help="Print the English translation.")
-    parser.add_argument("-i", "--id", action='store_true', help="Print the id of the phrase.")
-    parser.add_argument("-l", "--latin", action='store_true', help="Print the Latin phrase (default)")
-    parser.add_argument("-m", "--min", default=0, type=int, help="Set the minimum length of the Latin phrase")
-    parser.add_argument("-M", "--max", default=10000000, type=int, help="Set the maximum length of Latin phrase")
-    parser.add_argument("-n", "--notes", action='store_true', help="Print any notes on phrase")
+    parser = argparse.ArgumentParser(
+        description="Latin famous phrases in the terminal.")
+    parser.add_argument("-i", "--id",
+                        action='store_true',
+                        help="print the id of the phrase.")
+    parser.add_argument("-l", "--latin",
+                        action='store_true',
+                        help="print the Latin phrase (default)")
+    parser.add_argument("-e", "--english",
+                        action='store_true',
+                        help="print the English translation.")
+    parser.add_argument("-n", "--notes",
+                        action='store_true',
+                        help="print any notes on phrase")
+    parser.add_argument("-m", "--min",
+                        default=0,
+                        type=int,
+                        help="set the minimum length of the Latin phrase")
+    parser.add_argument("-M", "--max",
+                        default=10000000,
+                        type=int,
+                        help="set the maximum length of Latin phrase")
+    parser.add_argument("-p", "--num",
+                        action='store_true',
+                        help="print number of possibilities within constraints")
+    parser.add_argument("-f", "--file",
+                        default="/usr/share/phrases/phrases.csv",
+                        help="set the location of the phrase file")

     args = parser.parse_args()
 
     right_length = []
 
     args = parser.parse_args()
 
     right_length = []
 

-    # Find phrases of the right size
-    with open('/usr/share/phrases/phrases.csv') as f:
+    # convert csv file into list
+    with open(args.file) as f:

         reader = csv.reader(f)
         reader = csv.reader(f)

-        all_lines = list(reader)

         next(reader, None) # skip header
         next(reader, None) # skip header

-        for row in all_lines:
-            try:
-                if args.max >= int(row[4]) >= args.min: # generate a shortlist of phrases of the right length
-                    right_length.append(row[0])
-            except:
-                pass # skip malformed rows
-
-        try:
-            chosen = int(right_length[random.randint(0, len(right_length) - 1)]) # choose a random id from the shortlist
-        except:
-            sys.exit("No phrase within the given parameters!")
-
-        # Output as specified in flags
-        if not (args.english or args.latin or args.notes):
-            print(all_lines[chosen][1])
-        else:
-            if args.id:
-                print(all_lines[chosen][1])
-            if args.latin:
-                print(all_lines[chosen][1])
-            if args.english:
-                print(all_lines[chosen][2])
-            if args.notes:
-                print(all_lines[chosen][3])
+        all_lines = list(reader) 
+    f.close()
+
+    # iterate through all the phrases
+    for row in all_lines:
+        try: # generate a shortlist of phrases of the right length
+            if args.max >= int(row[4]) >= args.min:
+                right_length.append(row[0])
+        except: # skip malformed rows without exiting
+            pass
+
+    try: # choose a random id from the shortlist
+        chosen = int(right_length[random.randint(0, len(right_length) - 1)])
+    except:
+        sys.exit("No phrase within the given parameters!")
+
+    # Output as specified in flags
+    for row in all_lines:
+        if int(row[0]) == chosen:
+            if not (args.id
+                    or args.latin
+                    or args.english
+                    or args.notes
+                    or args.num):
+                print(row[1])
+            else:
+                if args.id:
+                    print(row[1])
+                if args.latin:
+                    print(row[1])
+                if args.english:
+                    print(row[2])
+                if args.notes:
+                    print(row[3])
+                if args.num:
+                    print(len(right_length))

 
 if __name__ == "__main__":
     main()
 
 if __name__ == "__main__":
     main()