hip-hop creation assistance tool

rapgod.py

#!/usr/bin/python2
'''
Impress your friends and become the next
2pac using rapgod.py, a state-of-the-art
rhymez and raps assistance tool.

dsc@dev4 $ rapgod en python
brighten  brighton  frighten   icahn
icon      ikon      lightning  lightson
ptyon     pythons   tighten    titan
triton    whiten
'''

import argparse
import re
import string


logo = r"""
                   ___          _
 _ __ __ _ _ __   / _ \___   __| |
| '__/ _` | '_ \ / /_\/ _ \ / _` |
| | | (_| | |_) / /_\\ (_) | (_| |
|_|  \__,_| .__/\____/\___/ \__,_|
          |_|
""".strip('\n')


def fetch(source, word):
    import requests
    
    headers = {
        "User-Agent": "Mozilla/5.0 AppleWebKit/539.40 (KHTML, like Gecko) Chrome/62.0.4.80"
    }
    r = requests.get(source % word, headers=headers)
    r.raise_for_status()
    return r.content


def nl_parser(content):
    from bs4 import BeautifulSoup
    
    soup = BeautifulSoup(content, "html.parser")
    for h2 in soup.findAll("h2", attrs={"class": "bigblue"}):
        h2_title = h2.text.lower()
        if h2_title.startswith(("rijmwoordenboek", "uitdrukkingen")):
            continue
        if "woorden" not in h2_title:
            continue

        table = h2.next_sibling
        if table.name != "table":
            continue

        words = str(table)
        delimiter = ""

        for your_anti_crawling_sucks in ["br", "/br", "br/"]:
            if "<%s>" % your_anti_crawling_sucks in words:
                delimiter = "<%s>" % your_anti_crawling_sucks
                break

        words = filter(None, [re.sub(r'<[^>]*?>', '', z).decode("utf8") for z in words.split(delimiter)])
        return words[::-1]


def en_parser(content):
    from bs4 import BeautifulSoup
    
    soup = BeautifulSoup(content, "html.parser")
    words = []
    for a in soup.findAll("a", attrs={"href": re.compile('^d=.*$')}):
        if a.text.startswith("-"):
            continue
        words.append(a.text)

    return words


def val_words(words):
    def val_word(word):
        if len(word) <= 3:
            return
        return word
    rtn = []
    for word in words:
        word = filter(lambda x: x in string.printable, word)
        if not word:
            continue
        if " " in word:
            spl = word.split(" ", 1)
            if not val_word(spl[0]) or not val_word(spl[1]):
                continue
        if not val_word(word):
            continue
        rtn.append(word)
    return rtn


def output(words):
    from tabulate import tabulate
    
    words = val_words(words)
    if not words:
        print("no results")
        return

    data = (words[i : i+4] for i in range(0, len(words), 4))
    table = tabulate(data, tablefmt="plain", stralign="left")
    print(table)

    
word_sources = {
    "en": "https://www.rhymezone.com/r/rhyme.cgi?typeofrhyme=perfect&loc=thesql&Word=%s",
    "nl": "http://www.mijnwoordenboek.nl/rijmwoordenboek/%s"
}
    
parsers = {
    "en": en_parser,
    "nl": nl_parser
}


def main():
    # Just in case we have some parsers without corresponding sources or vice versa
    langs = set(word_sources) & set(parsers)
    
    parser = argparse.ArgumentParser(description=logo, formatter_class=argparse.RawDescriptionHelpFormatter)
    parser.add_argument('lang', choices=langs, help='language for which rhymes should be obtained')
    parser.add_argument('word', help='word which rhymes will be obtained for')
    
    args = parser.parse_args()
    
    try:
        raw = fetch(word_sources[args.lang], args.word)
        words = parsers[args.lang](raw)
        output(words)
    except ImportError:
        print("Missing rapgod.py requirements. Try: pip install requests beautifulsoup4 tabulate")
    except Exception as e:
        print("Oops! rapgod.py failed because: %r" % e)
 

if __name__ == '__main__':
    main()