From 708255c5b500f47c4bcc1f48fbd385fc62966685 Mon Sep 17 00:00:00 2001
From: Kamo Petrosyan <kamo@haikson.com>
Date: Thu, 25 Jun 2015 17:45:43 +0600
Subject: [PATCH] Release

---
 pysitemap/__init__.py |  1 +
 pysitemap/crawler.py  | 84 +++++++++++++++++++++++++++++++++++++++++++
 run.py                | 13 +++++++
 setup.py              | 37 +++++++++++++++++++
 4 files changed, 135 insertions(+)
 create mode 100644 pysitemap/__init__.py
 create mode 100644 pysitemap/crawler.py
 create mode 100644 run.py
 create mode 100644 setup.py

diff --git a/pysitemap/__init__.py b/pysitemap/__init__.py
new file mode 100644
index 0000000..e71f191
--- /dev/null
+++ b/pysitemap/__init__.py
@@ -0,0 +1 @@
+from crawler import Crawler
\ No newline at end of file
diff --git a/pysitemap/crawler.py b/pysitemap/crawler.py
new file mode 100644
index 0000000..e4932ab
--- /dev/null
+++ b/pysitemap/crawler.py
@@ -0,0 +1,84 @@
+import urllib
+from bs4 import BeautifulSoup
+import urlparse
+import mechanize
+import pickle
+import re
+
+
+
+class Crawler:
+    def __init__(self, url, outputfile='sitemap.xml', logfile='error.log', oformat='xml'):
+        # Set the startingpoint for the spider and initialize 
+        # the a mechanize browser object
+        self.url = url
+        self.br = mechanize.Browser()
+        self.logfile = open(logfile, 'a')
+        self.oformat = oformat
+        self.outputfile = outputfile
+
+        # create lists for the urls in que and visited urls
+        self.urls = [url]
+        self.visited = [url]
+        self.excepted = []
+        self.exts = ['htm', 'php']
+        self.allowed_regex = '(\w+)\.((?!htm)(?!rar)\w+)$'
+
+    def set_exts(self, exts):
+        self.exts = exts
+
+    def allow_regex(self, regex=None):
+        if not regex is None:
+            self.allowed_regex = regex
+        else:
+            allowed_regex = ''
+            for ext in self.exts:
+                allowed_regex += '(!{})'.format(ext)
+            self.allowed_regex = '(\w+)\.({}\w+)$'.format(allowed_regex)
+
+    def crawl(self):
+        self.regex = re.compile(self.allowed_regex)
+        while len(self.urls)>0:
+            try:
+                self.br.open(self.urls[0])
+                for link in self.br.links():
+                    newurl =  urlparse.urljoin(link.base_url,link.url)
+                    #print newurl
+                    if self.is_valid(newurl):
+                        self.visited.append(newurl)
+                        self.urls.append(newurl)
+            except Exception, e:
+                self.errlog(e.message)
+
+            self.urls.pop(0)
+
+        if self.oformat == 'xml':
+            self.write_xml()
+
+
+    def is_valid(self, url):
+        valid = False
+        if url in self.visited and not url in self.excepted:
+            return False
+        if not self.url in url:
+            return False
+        if re.search(self.regex, url):
+            return False
+        return True
+
+    def errlog(self, msg):
+        self.logfile.write(msg)
+        self.logfile.write('\n')
+
+    def write_xml(self):
+        of = open(self.outputfile, 'w')
+        of.write('<?xml version="1.0" encoding="utf-8"?><!--Generated by Screaming Frog SEO Spider 2,55-->\n')
+        of.write('<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9 http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd">\n')
+        url_str = '<url><loc>{}</loc></url>\n'
+        for url in self.visited:
+            of.write(url_str.format(url))
+
+        of.write('</urlset>')
+        of.close()
+
+
diff --git a/run.py b/run.py
new file mode 100644
index 0000000..9bb90a5
--- /dev/null
+++ b/run.py
@@ -0,0 +1,13 @@
+import pysitemap
+
+
+"""
+Example script
+"""
+
+if __name__=='__main__':
+    url = 'http://www.ltsvet.ru/' # url from to crawl
+    logfile = 'errlog.log' # path to logfile
+    oformat = 'xml' # output format
+    crawl = pysitemap.Crawler(url=url, logfile=logfile, oformat=oformat)
+    crawl.crawl()
\ No newline at end of file
diff --git a/setup.py b/setup.py
new file mode 100644
index 0000000..8d5fa8b
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,37 @@
+from distutils.core import setup
+from setuptools import find_packages, setup
+
+EXCLUDE_FROM_PACKAGES = []
+
+
+def get_version(major=0, minor=0, build=0):
+    return '%s.%s.%s' % (major, minor, build)
+
+
+setup(
+    name='pysitemap',
+    version=get_version(
+        major=0,
+        minor=2,
+        build=0,
+    ),
+    packages=find_packages(exclude=EXCLUDE_FROM_PACKAGES),
+    include_package_data=True,
+    url='https://github.com/Haikson/pysitemap',
+    license='GPL3',
+    author='Kamo Petrosyan',
+    author_email='kamo@haikson.com',
+    description='web crawler and sitemap generator.',
+    classifiers=[
+        'Development Status :: Release',
+        'Environment :: Web Environment',
+        'Intended Audience :: Developers',
+        'License :: OSI Approved :: BSD License',
+        'Operating System :: OS Independent',
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 2',
+        'Programming Language :: Python :: 2.7',
+        'Topic :: Software Development :: Libraries :: Python Modules',
+    ],
+    requires=['beautifulsoup4', 'mechanize']
+)
\ No newline at end of file