From cf207e7af18abf69ee9e4be21fb41efa32064cd3 Mon Sep 17 00:00:00 2001
From: Mitch Weaver <20451170+MitchWeaver@users.noreply.github.com>
Date: Mon, 23 Apr 2018 18:01:54 +0200
Subject: [PATCH] fix gitignore

remove
---
 .gitignore     |  1 +
 text-scaper.py | 29 -----------------------------
 2 files changed, 1 insertion(+), 29 deletions(-)
 delete mode 100755 text-scaper.py

diff --git a/.gitignore b/.gitignore
index 5051b0e..cfcba2c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,5 +1,6 @@
 *.pyc
 *.core
 text-scraping.py
+text-scraper.py
 notes
 notes.md
diff --git a/text-scaper.py b/text-scaper.py
deleted file mode 100755
index a6f140a..0000000
--- a/text-scaper.py
+++ /dev/null
@@ -1,29 +0,0 @@
-#!/usr/bin/env python3
-from bs4 import BeautifulSoup
-from bs4.element import Comment
-import urllib.request
-
-def tag_visible(element):
-    if element.parent.name in ['style', 'script', 'head', 'title', 'meta', '[document]']:
-        return False
-    if isinstance(element, Comment):
-        return False
-    return True
-
-def text_from_html(body):
-    soup = BeautifulSoup(body, 'html.parser')
-    texts = soup.findAll(text=True)
-    visible_texts = filter(tag_visible, texts)  
-    lines = []
-    for line in visible_texts:
-        lines.append(line)
-    return lines
-
-    # return " ".join(t.strip() for t in visible_texts)
-
-url = 'https://www.metal-archives.com/bands/burzum'
-html = urllib.request.urlopen(url).read()
-
-for line in text_from_html(html):
-    if len(line) > 2:
-        print(line.strip())