How to retrieve URLs and text from web pages

[kshw]

Hi,

I’m new to programming. I’m currently learning python to write a web crawler to extract all text from a web page, in addition to, crawling to further URLs and collecting the text there. The idea is to place all the extracted text in a .txt file with each word in a single line. So the text has to be tokenized. All punctuation marks, duplicate words and non-stop words have to be removed.

The program should crawl the web to a certain depth and collect the URLs and text from each depth (level). I decided to choose a depth of 3. I divided the code to two parts. Part one to collect the URLs and part two to extract the text. Here is my problem:

1. The program is extremely slow.
2. I'm not sure if it functions properly.
3. Is there a better way to extract text?
4. Are there any available modules to help clean the text i.e. removing duplicates, non-stop words ...

(Please Note: the majority of the code (the first part) is written by “James Mills”. I found the code online and it looks helpful so I used it. I just modified it and added my code to it)

Thanks,
Kal

import sys
import urllib2
import urlparse
from BeautifulSoup import BeautifulSoup,NavigableString
 
__version__ = "0.1"
__copyright__ = "CopyRight (C) 2008 by James Mills"
__license__ = "GPL"
__author__ = "James Mills"
__author_email__ = "James Mills, James dot Mills st dotred dot com dot au"
 
USAGE = "%prog [options] <url>"
VERSION = "%prog v" + __version__
 
AGENT = "%s/%s" % (__name__, __version__)
 
def encodeHTML(s=""):
    """encodeHTML(s) -> str
 
    Encode HTML special characters from their ASCII form to
    HTML entities.
    """
 
    return s.replace("&", "&amp;") \
            .replace("<", "&lt;") \
            .replace(">", "&gt;") \
            .replace("\"", "&quot;") \
            .replace("'", "'") \
            .replace("--", "&mdash")
 
class Fetcher(object):
 
    def __init__(self, url):
        self.url = url
        self.urls = []
 
    def __contains__(self, x):
        return x in self.urls
 
    def __getitem__(self, x):
        return self.urls[x]
 
    def _addHeaders(self, request):
        request.add_header("User-Agent", AGENT)
 
    def open(self):
        url = self.url
        #print "\nFollowing %s" % url
        try:
            request = urllib2.Request(url)
            handle = urllib2.build_opener()
        except IOError:
            return None
        return (request, handle)
 
    def fetch(self):
        request, handle = self.open()
        self._addHeaders(request)
        if handle:
            soup = BeautifulSoup()
            try:
                content = unicode(handle.open(request).read(), errors="ignore")
                soup.feed(content)
                #soup = BeautifulSoup(content)
                tags = soup('a')
            except urllib2.HTTPError, error:
                if error.code == 404:
                    print >> sys.stderr, "ERROR: %s -> %s" % (error, error.url)
                else:
                    print >> sys.stderr, "ERROR: %s" % error
                tags = []
            except urllib2.URLError, error:
                print >> sys.stderr, "ERROR: %s" % error
                tags = []
            for tag in tags:
                try:
                    href = tag["href"]
                    if href is not None:
                        url = urlparse.urljoin(self.url, encodeHTML(href))
                        if url not in self:
                            #print " Found: %s" % url
                            self.urls.append(url)
                except KeyError:
                    pass
 
 
################################################################################
# I created 3 lists (root, level2 and level3).                                 #
# Each list saves the URLs of that level i.e. depth. I choose to create 3      #
# lists so I can have the flexibility of testing the text in each level. Also, #
# the 3 lists can be easily combined into one list.                            #
################################################################################
 
# Level1: 
root = Fetcher('http://www.wantasimplewebsite.co.uk/index.html')
root.fetch()
for url in root:
    if url not in root: # Avoid duplicate links 
       root.append(url)
 
print "\nRoot URLs are:"
for i, url in enumerate(root):
   print "%d. %s" % (i+1, url)
 
 
# Level2: 
level2 = []
for url in root: # Traverse every element(i.e URL) in root and fetch the URLs from it
    temp = Fetcher(url)
    temp.fetch()
    for url in temp:
        if url not in level2: # Avoid duplicate links 
           level2.append(url)
 
 
print "\nLevel2 URLs are:"
for i, url in enumerate(level2):
   print "%d. %s" % (i+1, url)
 
 
# Level3: 
level3 = []
for url in level2: # Traverse every element(i.e URL) in level2 and fetch the URLs from it
    temp = Fetcher(url)
    temp.fetch()
    for url in temp:
        if url not in level3: # Avoid duplicate links
           level3.append(url)
 
 
print "\nLevel3 URLs are:"
for i, url in enumerate(level3):
   print "%d. %s" % (i+1, url)
 
# 1. Traverse every link in the lists and extract its web page content.
# 2. Tokenize Text.
# 3. Remove stop-words (i.e. and, but, to...)
# 4. Remove duplicates
# 5. What about stemming?
# 6. Check the spelling.
# 7. Save the result in a file
 
 
 
html = urllib2.urlopen('http://www.wantasimplewebsite.co.uk/index.html').read()
soup = BeautifulSoup(html)
 
def printText(tags):
    for tag in tags:
        if tag.__class__ == NavigableString:
            print tag,
        else:
            printText(tag)
 
printText(soup.findAll("body"))