Bible Verse Fetcher

b

#!/Users/marcin/Sync/Home/dotfiles/bin/.env/bin/python3

# Bible verse fetcher. Put this script in your PATH, update the above path to
# python, and make it executable.
#
# Usage: b <verses> [optional flags]
#
# Example: b John 3:16-17
# Example: b John 3:16-17 --version NIV
#
# Improved version of the original from here:
# https://github.com/covode/bible-fetch

import sys
from bs4 import BeautifulSoup
import argparse
import requests
import subprocess
import time
from unidecode import unidecode
import urllib.parse


def parse_args():
    default_version = "NRSVUE"

    parser = argparse.ArgumentParser(
        description="Fetch Bible references from biblegateway.com"
    )
    parser.add_argument("reference", nargs="*", help="bible reference")
    parser.add_argument(
        "--version",
        nargs="?",
        help="translation (e.g. NIV, NLT)",
        default=default_version,
    )
    parser.add_argument(
        "--verse-numbers",
        action="store_true",
        default=False,
        help="print verse numbers (hidden by default)",
    )
    parser.add_argument(
        "--ascii",
        action="store_true",
        default=False,
        help="translate Unicode to ASCII (useful on Windows)",
    )
    parser.add_argument(
        "-d",
        "--discord",
        action="store_true",
        default=False,
        help="formats the verse for Discord",
    )

    if len(sys.argv) == 1:
        parser.print_help()
        sys.exit(1)
    args = parser.parse_args()
    return (
        " ".join(args.reference),
        args.version or default_version,
        args.verse_numbers,
        args.ascii,
        args.discord,
    )


def get_soup(query, version):
    query = urllib.parse.quote_plus(query)
    r = requests.get(
        "https://www.biblegateway.com/passage/?search=" + query + "&version=" + version
    )
    return BeautifulSoup(r.text, "html.parser")


def clean(tag):
    for t in tag.find_all("sup"):
        if show_verse_numbers and "versenum" in t["class"]:
            continue
        t.decompose()
    if not show_verse_numbers:
        for t in tag.find_all(class_="chapternum"):
            t.decompose()
    for t in tag.find_all(class_="surface"):
        t.decompose()


def render(tag):
    clean(tag)
    text = ""
    for t in tag.descendants:
        if isinstance(t, str):
            text += t
        elif t.name == "br":
            text += "\n"
    return text


def get_passages(soup):
    passages = soup.find_all(class_="passage-table")
    if passages is None:
        return
    text = ""
    for p in passages:
        text += get_passage(p) + "\n\n"
    return text.replace('  ', ' ').strip()


def get_passage(soup):
    root = soup.find(class_="result-text-style-normal")
    if root is None:
        return
    passage = " ".join(map(lambda t: render(t), root.select("p, div.poetry p")))
    return passage


def get_verses(soup):
    verses = soup.find_all(class_="passage-table")
    if verses is None:
        return
    text = "; ".join([get_verse(v) for v in verses])
    return text


def get_verse(soup):
    root = soup.find(class_="dropdown-display-text")
    if root is None:
        return
    verse = ", ".join(root.descendants)
    return verse


def clean_whitespace(text):
    UNICODE_WHITESPACE_CHARACTERS = [
        "\u0009", # character tabulation
        "\u000a", # line feed
        "\u000b", # line tabulation
        "\u000c", # form feed
        "\u000d", # carriage return
        "\u0020", # space
        "\u0085", # next line
        "\u00a0", # no-break space
        "\u1680", # ogham space mark
        "\u2000", # en quad
        "\u2001", # em quad
        "\u2002", # en space
        "\u2003", # em space
        "\u2004", # three-per-em space
        "\u2005", # four-per-em space
        "\u2006", # six-per-em space
        "\u2007", # figure space
        "\u2008", # punctuation space
        "\u2009", # thin space
        "\u200A", # hair space
        "\u2028", # line separator
        "\u2029", # paragraph separator
        "\u202f", # narrow no-break space
        "\u205f", # medium mathematical space
        "\u3000", # ideographic space
    ]

    for char in UNICODE_WHITESPACE_CHARACTERS:
        text = text.replace(char, " ")

    # Consolidate multiple spaces into one.
    return " ".join(text.split())


def format_discord(passage):
    return f"*{passage}*"


query, version, show_verse_numbers, use_ascii, discord = parse_args()
soup = get_soup(query, version)
passages = get_passages(soup)
passages = clean_whitespace(passages)
verses = get_verses(soup)

if use_ascii:
    passages = unidecode(passages)
if discord:
    passages = format_discord(passages)
if passages is not None:
    print(passages)
    print(f"~ {verses}")

    # Copy the output to the clipboard.
    if discord:
        subprocess.run("pbcopy", text=True, input=f"{passages}\n~ {verses}")
    else:
        subprocess.run("pbcopy", text=True, input=verses)
        time.sleep(0.5)
        subprocess.run("pbcopy", text=True, input=passages)
    print()
    print("Passage(s) copied to clipboard!")