current

main.py

@@ -1,4 +1,3 @@
-import itertools
 import re
 import string
 import sys
@@ -10,86 +9,10 @@ from bs4 import BeautifulSoup
 from loguru import logger
 from tqdm import tqdm
 
-base = Path('./xml/Matthew Henry Commentary 2').absolute()
+base = Path('./xml/Matthew Henry Commentary').absolute()
 
 logger.remove(0)
-
-from functools import partialmethod
-
-logger.__class__.foobar = partialmethod(logger.__class__.log, "foobar", level='WARNING')
-logger.add('log.txt', level='WARNING')
-
-convert = dict([
-("Eccl", "Ecclesiastes"),
-("Rom", "Romans"),
-("2Tim", "2Timothy"),
-("2Pet", "2Peter"),
-("Gen", "Genesis"),
-("John", "John"),
-("1Cor", "1Corinthians"),
-("Ezek", "Ezekiel"),
-("Heb", "Hebrews"),
-("Rev", "Revelation"),
-("Eph", "Ephesians"),
-("Isa", "Isaiah"),
-("Ps", "Psalms"),
-("Acts", "Acts"),
-("Deut", "Deuteronomy"),
-("Neh", "Nehemiah"),
-("1Chr", "1Chronicles"),
-("2Kgs", "2Kings"),
-("2Cor", "2Corinthians"),
-("Hos", "Hosea"),
-("Exod", "Exodus"),
-("Matt", "Matthew"),
-("Job", "Job"),
-("Prov", "Proverbs"),
-("Col", "Colossians"),
-("Jer", "Jeremiah"),
-("1John", "1John"),
-("Jas", "James"),
-("1Tim", "1Timothy"),
-("Amos", "Amos"),
-("Mic", "Micah"),
-("Dan", "Daniel"),
-("Jonah", "Jonah"),
-("Luke", "Luke"),
-("Mal", "Malachi"),
-("Zech", "Zechariah"),
-("Phil", "Philippians"),
-("Mark", "Mark"),
-("2Thess", "2Thessalonians"),
-("Jude", "Jude"),
-("1Sam", "1Samuel"),
-("Num", "Numbers"),
-("Gal", "Galatians"),
-("1Pet", "1Peter"),
-("Lev", "Leviticus"),
-("2Chr", "2Chronicles"),
-("Lam", "Lamentations"),
-("1Kgs", "1Kings"),
-("Ezra", "Ezra"),
-("Obad", "Obadiah"),
-("Hab", "Habakkuk"),
-("2Sam", "2Samuel"),
-("Josh", "Joshua"),
-("Judg", "Judges"),
-("Ruth", "Ruth"),
-("Esth", "Esther"),
-("Phlm", "Philemon"),
-("1Thess", "1Thessalonians"),
-("Joel", "Joel"),
-("Titus", "Titus"),
-("3John", "3John"),
-("Zeph", "Zephaniah"),
-("Song", "Song of Songs"),
-("Hag", "Haggai"),
-("2John", "2John"),
-("Nah", "Nahum"),
-("Psa", "Psalms"),
-("2Peter", "2Peter")
-]
-)
+logger.add('log.txt')
 
 class MyHTMLParser(HTMLParser):
     file = None
@@ -229,17 +152,15 @@ class MyHTMLParser(HTMLParser):
 
                 file.write(line)
 
-    def normalize_osis_verses(self, verses):
-        """Takes this
-        'Bible:John.1.3 Bible:John.1.10 Bible:Eph.3.9 Bible:Col.1.16 Bible:Heb.1.2 Bible:Acts.17.24-Acts.17.25 Bible:Exod.5.26 Bible:Gen.5'
+    @staticmethod
+    def normalize_osis_verses(verses):
+        """Takes this 'Bible:John.1.3 Bible:John.1.10 Bible:Eph.3.9 Bible:Col.1.16 Bible:Heb.1.2 Bible:Acts.17.24-Acts.17.25'
         and turns it into somthing more readable"""
         normalized_refs = list()
         for chunks in verses.removeprefix("Bible:").split('Bible:'):
             spanned_verses = list()
             for ref in chunks.split('-'):
                 verse = ref.replace('.', ' ', 1).replace('.', ':')
-                book = ref.split('.')[0]
-                verse.replace(book, convert[book])
                 spanned_verses.append(
                     bible.format_scripture_references(
                         bible.get_references(verse.strip())
@@ -253,57 +174,16 @@ class MyHTMLParser(HTMLParser):
             except:
                 logger.warning(f"Error with: {verses=}: {spanned_verses=}")
                 raise
-
-            if normalized is False:
-                print(f"Error with: {verses=}: {spanned_verses=}")
-                sys.exit()
-
             normalized_refs.append(normalized)
 
         return ';'.join(normalized_refs)
 
-    # @staticmethod
-    def old_normalize_osis_verses(self, verses):
-        """Takes this
-        'Bible:John.1.3 Bible:John.1.10 Bible:Eph.3.9 Bible:Acts.17.24-Acts.17.25 Bible:Exod.5.26 Bible:Gen.5'
-        and turns it into somthing more readable"""
-        normalized_refs = list()
-        for chunks in verses.removeprefix("Bible:").split('Bible:'):
-            spanned_verses = chunks.split('-')
-            if len(spanned_verses) < 2:
-                spanned_verses = list(itertools.repeat(spanned_verses[0], 2))
-
-            book, start_chapter, start_verse = spanned_verses[0].split('.')
-            _, end_chapter, end_verse = spanned_verses[1].split('.')
-            book = bible.Book[convert[book].upper()]
-
-            normalized = bible.NormalizedReference(
-                book=book,
-                start_chapter=start_chapter,
-                start_verse=start_verse,
-                end_chapter=end_chapter,
-                end_verse=end_verse,
-            )
-
-            if normalized is False:
-                logger.foobar(f'{self.args=}')
-
-            normalized_refs.append(
-                bible.format_scripture_references([normalized]).strip()
-            )
-
-        return ';'.join(normalized_refs)
-
     @staticmethod
-    @logger.catch(reraise=False)
     def obsidian_links(verses):
         """Take `Book Chapter:Ver-Ver and turn it into a obsidian bible link"""
         links = []
         for verse in verses.split(';'):
-            verse = verse.replace(':', '#').replace('-', '..')
-            if verse[0] in string.digits:
-                verse.replace(' ', '', 1)
-            links.append(f"[[{verse}]]")
+            links.append(f"[[{verse.replace(':', '#').replace('-', '..')}]]")
 
         return '; '.join(links)
 
@@ -357,10 +237,9 @@ class MyHTMLParser(HTMLParser):
                             self.attrs['osisref']
                         )
                     else:
-                        # verses = self.normalize_osis_verses(
-                        #     self.convert_passage(self.attrs['passage'])
-                        # )
-                        raise ValueError('No `osisref` in tag attrs')
+                        verses = self.normalize_osis_verses(
+                            self.convert_passage(self.attrs['passage'])
+                        )
 
                     self.write_to_file(self.obsidian_links(verses))
 
@@ -377,22 +256,15 @@ class MyHTMLParser(HTMLParser):
                                 logger.debug(self.passage_verse)
                                 raise
 
-                            if verse.start_verse == verse.end_verse:
-                                self.write_to_file('## Verse: ')
-                                self.write_to_file(
-                                    f'{verse.start_verse}'
-                                )
-                            else:
-                                self.write_to_file('## Verses: ')
-                                self.write_to_file(
-                                    f'{verse.start_verse} - {verse.end_verse}'
-                                )
+                            self.write_to_file('## Verses: ')
+                            self.write_to_file(
+                                f'{verse.start_verse} - {verse.end_verse}'
+                            )
                             self.write_to_file('\n\n')
 
                         # Need this do the regex in self.clean does not pick
                         # this up. Will be also cleaned in the same function.
                         self.write_to_file('Passage: ')
-
                 if self.tag_type == 'end':
                     self.write_to_file('\n\n')
 

matty.py

@@ -1,30 +1,28 @@
 import time
 from typing import Any
+from pathlib import Path
 
 import scrapy
 from scrapy.http import Response
 
 from loguru import logger
 
-# logger.remove(0)
-logger.add('pages.txt')
+logger.remove(0)
+# logger.add('pages.txt')
 
 
 class spider(scrapy.Spider):
     name = 'matty'
+    base_folder = Path('./scraps/').absolute()
+    # allowed_domains = ['https://www.biblegateway.com/']
     base_url = 'https://www.biblegateway.com/resources/matthew-henry'
     start_urls = [f'{base_url}/toc']
 
     custom_settings = {
-        "AUTOTHROTTLE_ENABLED": True,
-        # 'DOWNLOAD_DELAY': 2.5,
+        # "AUTOTHROTTLE_ENABLED": True,
+        # 'DOWNLOAD_DELAY': 1.5,
     }
 
-    books = 0
-    chapters = 0
-    sections = 0
-
-
     def parse(self, response: Response, **kwargs: Any) -> Any:
         self.crawler.stats.set_value('books', 0)
         self.crawler.stats.set_value('chapters', 0)
@@ -35,18 +33,52 @@ class spider(scrapy.Spider):
             self.crawler.stats.inc_value('books')
             yield response.follow(a, callback=self.parse_book)
 
+
     def parse_book(self, response: Response, **kwargs: Any) -> Any:
         # for a in response.copy().css('div.article a').getall():
         #     logger.info(a)
 
-        for a in response.css('ul.resource-list a').getall():
-            if 'Chapter' in a:
-                self.crawler.stats.inc_value('chapters')
-                # logger.info(f"Chapter: {a}")
-                # yield response.follow(a, callback=self.parse_chapter)
+        # book = response.url.split(r'/')[-1]
 
-            if 'Verse' in a:
-                self.crawler.stats.inc_value('sections')
-                # logger.info(f"Verse: {a}")
-                # yield response.follow(a, callback=self.parse_verses)
+        for a in response.css('ul.resource-list a'):
+            logger.debug(a)
+            # if 'Chapter' in a:
+            self.crawler.stats.inc_value('chapters')
+            # logger.info(f"Chapter: {a}")
 
+            if 'CHAPTER' in a.css('::text')[0].get().upper():
+                yield response.follow(a, callback=self.get_chapter)
+            else:
+                yield response.follow(a, callback=self.get_data)
+            # break
+            # if 'Verse' in a:
+            #     self.crawler.stats.inc_value('sections')
+            # logger.info(f"Verse: {a}")
+            # yield response.follow(a, callback=self.parse_verses)
+
+        file_name = response.url.split('/')[-1].replace('.', '_') + '.html'
+        logger.warning(file_name)
+        data = response.css('div.article p').getall()
+        self.write_data(file_name, data)
+
+    def get_data(self, response: Response, **kwargs: Any) -> Any:
+        file_name = response.url.split('/')[-1].replace('.', '_') + '.html'
+        logger.warning(file_name)
+        data = response.css('div.article p').getall()
+        self.write_data(file_name, data)
+
+    def get_chapter(self, response: Response, **kwargs: Any) -> Any:
+        file_name = response.url.split('/')[-1].replace('.', '_') + '.html'
+        file_name = f'chapter_{file_name}'
+        logger.warning(file_name)
+        data = response.css('div.article p').getall()
+        self.write_data(file_name, data)
+
+    def write_data(self, filename, data):
+        file = self.base_folder / filename
+        file.parent.mkdir(exist_ok=True, parents=True)
+
+        with open(file, 'w+') as f:
+            for d in data:
+                f.write(d)
+                f.write('\n')