From 9d2c4f631bf962f071846f3a92a42fe032e504ac Mon Sep 17 00:00:00 2001
From: bMorgan01 <ben.morgan5000@gmail.com>
Date: Thu, 1 Sep 2022 08:10:55 -0600
Subject: [PATCH] init commit

---
 crawl.conf |   9 ++++
 main.py    | 120 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 129 insertions(+)
 create mode 100644 crawl.conf
 create mode 100644 main.py

diff --git a/crawl.conf b/crawl.conf
new file mode 100644
index 0000000..791304a
--- /dev/null
+++ b/crawl.conf
@@ -0,0 +1,9 @@
+# Domain                    Ex: benrmorgan.com
+benrmorgan.com
+# Prefix                    Ex: http://www.
+http://www.
+# Target path               Ex /var/www/html/sitemap.xml or ./sitemaps/sitemap.xml
+./
+# Ignore urls containing    Ex: /files/
+/files/
+/images/
\ No newline at end of file
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..9a9c655
--- /dev/null
+++ b/main.py
@@ -0,0 +1,120 @@
+import datetime
+import os
+
+import bs4
+from urllib.request import Request, urlopen
+from os.path import exists
+from shutil import move
+import language_tool_python
+tool = language_tool_python.LanguageTool('en-US')
+
+
+def spider(prefix, domain, exclude):
+    return spider_rec(dict(), prefix, domain, "/", exclude)
+
+
+def spider_rec(links, prefix, domain, postfix, exclude):
+    req = Request(prefix + domain + postfix)
+    html_page = urlopen(req)
+
+    soup = bs4.BeautifulSoup(html_page, "lxml")
+
+    links[postfix] = soup.getText()
+    for link in soup.findAll('a'):
+        href = link.get('href')
+        if "mailto:" not in href and (domain in href or href[0] == '/'):
+            if href not in links.keys():
+                found = False
+                for d in exclude:
+                    if d in href:
+                        found = True
+                        break
+
+                if found:
+                    continue
+
+                href = href.replace(" ", "%20")
+                if domain in href:
+                    spider_rec(links, "", "", href, exclude)
+                else:
+                    spider_rec(links, prefix, domain, href, exclude)
+
+    return links
+
+
+def cmp(p1, p2):
+    with open(p1, 'r') as f1:
+        with open(p2, 'r') as f2:
+            l1 = f1.readlines()
+            l2 = f2.readlines()
+            not_matched = []
+
+            if len(l1) == len(l2):
+                for i in range(len(l1)):
+                    if l1[i] != l2[i]:
+                        return False
+            else:
+                return False
+
+    return True
+
+
+def main():
+    print("Reading conf...")
+
+    conf = []
+    with open('crawl.conf', 'r') as file:
+        for line in file.readlines():
+            if line[0] != '#':
+                line = line.replace("\n", "")
+                line = line.replace("\r", "")
+                conf.append(line)
+
+    domain = conf[0]
+    prefix = conf[1]
+    path = conf[2]
+
+    ignores = conf[3::]
+
+    print("Crawling site...")
+    links = spider(prefix, domain, ignores)
+    date = datetime.datetime.utcnow()
+
+    existed = exists(path)
+    oldpath = path
+    if existed:
+        print("Report already exists, creating temp...")
+        path = "newReport.txt"
+
+    # print("Writing to target file...")
+    # out = open(path, 'w')
+    # out.write("\tSpelling Spider by Ben Morgan - www.benrmorgan.com\n\n")
+
+    for l in links.keys():
+        strippedLines = [s.strip() for s in links[l].split('\r\n') if s.strip()]
+        strippedLines += [s.strip() for s in links[l].split('\n') if s.strip()]
+        uniqueLines = []
+        for line in strippedLines:
+            if line not in uniqueLines:
+                uniqueLines.append(line)
+
+        text = os.linesep.join(uniqueLines)
+        matches = tool.check(text)
+        print(matches)
+
+        for match in matches:
+            print(match.message)
+            print(match.context[:match.offsetInContext-1] + "\033[91m {}\033[00m" .format(match.context[match.offsetInContext:match.offsetInContext+match.errorLength]) + match.context[match.offsetInContext+match.errorLength::])
+
+    # if existed and not cmp(oldpath, path):
+    #     print("Creating old report backup...")
+    #     move(oldpath, oldpath + "-old")
+    #     print("Overwriting old report with new one...")
+    #     move(path, oldpath)
+    # elif existed:
+    #     print("Reports are the same, removing temp...")
+    #     os.remove(path)
+
+    print("Done.")
+
+main()
\ No newline at end of file