Last active
August 29, 2015 14:22
-
-
Save nbr23/380e1e32145acf2407da to your computer and use it in GitHub Desktop.
Irregular verbs list
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #! /usr/bin/python3 | |
| import sqlite3 | |
| import urllib.request | |
| from bs4 import BeautifulSoup | |
| import sys | |
| def get_verbs(page, verbslist): | |
| baseurl = "http://pasttenses.com/irregular-verbs-list" + page | |
| data = urllib.request.urlopen(baseurl) | |
| soup = BeautifulSoup(data) | |
| verbs_table = soup.find('table') | |
| verbs = verbs_table.find_all('tr') | |
| for verb in verbs: | |
| i = 0 | |
| k = 0 | |
| tenses = verb.find_all('td') | |
| forms = {} | |
| for tense in tenses: | |
| if i in (0, 3, 4): | |
| forms[k] = tense.get_text() | |
| k += 1 | |
| i += 1 | |
| if k > 0: | |
| verbslist.append(forms) | |
| def get_all_pages(): | |
| verbslist = [] | |
| for i in range(1, 14): | |
| if i == 1: | |
| get_verbs("", verbslist) | |
| else: | |
| get_verbs("-page%i" % i, verbslist) | |
| return verbslist | |
| def fill_db(fname): | |
| conn = sqlite3.connect(fname) | |
| c = conn.cursor() | |
| c.execute('CREATE TABLE verbs_en (id INTEGER PRIMARY KEY, infinitive TEXT, past TEXT, participle TEXT);') | |
| verbslist = get_all_pages() | |
| for verbs in verbslist: | |
| c.execute('INSERT INTO verbs_en (infinitive, past, participle) VALUES ("%s", "%s", "%s");' % (verbs[0], verbs[1], verbs[2])) | |
| conn.commit() | |
| conn.close() | |
| if len(sys.argv) < 2: | |
| print("Usage: %s <db_filename>" % sys.argv[0]) | |
| sys.exit(1) | |
| else: | |
| fill_db(sys.argv[1]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment