X-Git-Url: https://git.armaanb.net/?p=phrases.git;a=blobdiff_plain;f=extract.py;h=4a0a6b00cb3b44a01e3b02e54506dcd6197379b7;hp=c83755fd1caf2f655299112cb37bb86e05caf9dd;hb=HEAD;hpb=5d6d1f218d5ef88042daaeb6c4ef397b7a233be3

diff --git a/extract.py b/extract.py
index c83755f..4a0a6b0 100755
--- a/extract.py
+++ b/extract.py
@@ -1,27 +1,30 @@
 #!/usr/bin/env python3
-# Extract Latin famous phrases from wikipedia
-# Armaan Bhojwani 2020
+# Extract Latin famous phrases from Wikipedia
+# Armaan Bhojwani 2021
 
 import argparse
 import sqlite3
 import requests
 from bs4 import BeautifulSoup
 
+
 def parse_args():
     parser = argparse.ArgumentParser(
-        description="Generate SQLite db of Latin famous phrases from Wikipedia.")
+        description="Generate database of Latin famous phrases from Wikipedia")
     parser.add_argument("-o", "--output",
-                       default="phrases.db",
-                       help="set custom output file location")
+                        default="phrases.db",
+                        help="set custom output file location")
     parser.add_argument("-v", "--version",
-                        action="store_true",
-                        help="print script version")
+                        action="version",
+                        version="phrases-extract 1.0.3")
     return parser.parse_args()
 
+
 def get_html(url):
     print("downloading webpage")
     return BeautifulSoup(requests.get(url).content, "html.parser")
 
+
 def prep_database():
     print("prepping database")
     c.execute("DROP TABLE IF EXISTS phrases")
@@ -32,8 +35,9 @@ def prep_database():
               notes TEXT,
               length INTEGER)""")
 
+
 def fill_database(list_table):
-    i = 0 # phrase id
+    i = 0  # phrase id
     print("iterating through tables")
     for table in list_table:
         for row in table.tbody.find_all("tr", recursive=False):
@@ -44,28 +48,27 @@ def fill_database(list_table):
                 latin = (cell[0].get_text(" ", strip=True)).rstrip()
                 english = (cell[1].get_text(" ", strip=True)).rstrip()
                 notes = (cell[2].get_text(" ", strip=True)).rstrip()
-    
+
                 c.execute("""INSERT INTO phrases
                          (id, latin, english, notes, length)
                          VALUES(?, ?, ?, ?, ?)""",
-                         (i, latin, english, notes, len(latin)))
+                          (i, latin, english, notes, len(latin)))
                 conn.commit()
             i = i + 1
 
+
 def get_tables():
     url = ("""https://en.wikipedia.org/w/index.php?title=List_of_Latin_phrases_(
           full)&oldid=986793908""")
-    return get_html(url).find_all("table", attrs={"class":"wikitable"})
+    return get_html(url).find_all("table", attrs={"class": "wikitable"})
+
 
 def main():
-    if args.version:
-        print(version)
-    else:
-        prep_database()
-        fill_database(get_tables())
+    prep_database()
+    fill_database(get_tables())
+
 
 if __name__ == "__main__":
-    version = "phrases extract.py 1.0.1"
     args = parse_args()
     conn = sqlite3.connect(args.output)
     c = conn.cursor()