Created
April 20, 2022 17:49
-
-
Save paulgrammer/bb3c9ad79b75715b3b032fc06b390056 to your computer and use it in GitHub Desktop.
This file contains 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
| import os | |
| import re | |
| import sys | |
| from glob import glob | |
| from urllib.request import urlopen | |
| import requests | |
| from bs4 import BeautifulSoup | |
| EN_URL = "https://www.jw.org/en/library/bible/nwt/books/" | |
| LG_URL = "https://www.jw.org/lg/layibulale/bayibuli/nwt/ebitabo/" | |
| def get_books(lang_url): | |
| url = requests.get(lang_url) | |
| page =BeautifulSoup(url.text, 'lxml') | |
| books = page.find('select', attrs={'id':'Book'}).text.split('\n')[1:] | |
| for i in range(len(books)): | |
| if(len(books[i].split()) > 1): | |
| hyphen_join = books[i].split() | |
| books[i] = '-'.join(hyphen_join) | |
| return books | |
| en_books = get_books(EN_URL) | |
| en_books.remove('') | |
| lg_books = get_books(LG_URL) | |
| lg_books.remove('') | |
| def write_book_to_file(sub_url, book,lang): | |
| for i in range(len(book)): | |
| os.makedirs("Scrapped/"+lang+book[i]) | |
| address = sub_url + book[i] | |
| print(address) | |
| url = requests.get(address) | |
| page = BeautifulSoup(url.text, 'lxml') | |
| chapters = page.find('div', attrs={'class': 'chapters cms-clearfix'}).text.split('\n')[1:] | |
| chapters.remove('') | |
| ## Get Chapters for Each book | |
| for ch in chapters: | |
| url1 = requests.get(sub_url + book[i] +'/' + ch) | |
| print(sub_url + book[i] +'/' + ch) | |
| page1 = BeautifulSoup(url1.text,'lxml') | |
| ch1 = page1.find('div',attrs={'id': "bibleText"}) | |
| tt = [ | |
| verses.text.replace(u'\xa0', u' ').replace('\n',' ').replace('+', '').replace('*', '') for verses in ch1.find_all('span',attrs={'class':'verse'})] | |
| chapter = open("Scrapped/"+lang+book[i]+"/"+str(ch) + ".txt", 'w') | |
| for item in tt: | |
| chapter.write("{}\n".format(item)) | |
| write_book_to_file(LG_URL, lg_books,"Luganda/") | |
| write_book_to_file(EN_URL, en_books,"English/") | |
| def merge_books(lang, books): | |
| file_lang = [] | |
| for bk in books: | |
| file_lang.append((glob("Scrapped/"+lang+"/" + bk + "/*.txt"))) | |
| with open("Scrapped/"+lang+"/merged.txt","wb") as write_file: | |
| for f in file_lang: | |
| for i in f: | |
| with open(i,'rb') as r: | |
| write_file.write(r.read()) | |
| merge_books("Luganda", lg_books) | |
| merge_books("English", en_books) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment