functionalized things

[phrases.git] / extract.py

diff --git a/extract.py b/extract.py
index 8f8877a8fd51968751022a80bc2272edb120de49..833594da483748f0608acaa5c143e88249d007e9 100755 (executable)
--- a/extract.py
+++ b/extract.py
@@ -4,27 +4,23 @@
 
 import argparse
 import sqlite3
-import sys
 import requests
 from bs4 import BeautifulSoup
 
-def main(args=sys.argv[1:]):
-    # Argument parsing
+def parse_args():
     parser = argparse.ArgumentParser(
         description="Generate SQLite db of Latin famous phrases from Wikipedia.")
     parser.add_argument("-o", "--output",
                        default="phrases.db",
                        help="set custom output file location")
-    args = parser.parse_args()
+    return parser.parse_args()
 
-    url = ("""https://en.wikipedia.org/w/index.php?title=List_of_Latin_phrases_(
-          full)&oldid=986793908""")
+def get_html(url):
     print("downloading webpage")
-    soup = BeautifulSoup(requests.get(url).content, "html.parser")
+    return BeautifulSoup(requests.get(url).content, "html.parser")
 
+def prep_database(c):
     print("prepping database")
-    conn = sqlite3.connect(args.output)
-    c = conn.cursor()
     c.execute("DROP TABLE IF EXISTS phrases")
     c.execute("""CREATE TABLE phrases(
               id INTEGER,
@@ -33,29 +29,36 @@ def main(args=sys.argv[1:]):
               notes TEXT,
               length INTEGER)""")
 
-    i = 0 # For the phrase id
-
-    # iterate through the tables in the page
-    list_table = soup.find_all("table", attrs={"class":"wikitable"})
+def fill_database(list_table, c, conn):
+    i = 0 # phrase id
     print("iterating through tables")
     for table in list_table:
         for row in table.tbody.find_all("tr", recursive=False):
             cell = row.find_all("td", recursive=False)
             if len(cell) > 2:
                 print(i, end="\r")
+
                 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)))
+                c.execute("""INSERT INTO phrases
+                         (id, latin, english, notes, length)
+                         VALUES(?, ?, ?, ?, ?)""",
+                         (i, latin, english, notes, len(latin)))
                 conn.commit()
-
             i = i + 1
 
-    print("closing database")
-    c.close()
-    conn.close()
+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"})
+
+def main(args):
+    conn = sqlite3.connect(args.output)
+    c = conn.cursor()
+    prep_database(c)
+    fill_database(get_tables(), c, conn)
 
 if __name__ == "__main__":
-    main()
+    main(parse_args())