scrapy (scraping) + whoosh (indexer) example

main.py

# http://stackoverflow.com/questions/23921986/web-scraping-without-knowledge-of-page-structure
_Author = Farsheed Ashouri
import os
import sys
import re
## Spider libraries
from scrapy.spider import BaseSpider
from scrapy.selector import Selector
from main.items import MainItem
from scrapy.http import Request
from urlparse import urljoin
## indexer libraries
from whoosh.index import create_in, open_dir
from whoosh.fields import *
## html to text conversion module
import nltk

def open_writer():
    if not os.path.isdir("indexdir"):
        os.mkdir("indexdir")
        schema = Schema(title=TEXT(stored=True), content=TEXT(stored=True))
        ix = create_in("indexdir", schema)
    else:
        ix = open_dir("indexdir")
    return ix.writer()

class Main(BaseSpider):
    name        = "main"
    allowed_domains = ["en.wikipedia.org"]
    start_urls  = ["http://en.wikipedia.org/wiki/Snakes"]

    def parse(self, response):
        writer = open_writer()  ## for indexing
        sel = Selector(response)
        email_validation = re.compile(r'^[_a-z0-9-]+(\.[_a-z0-9-]+)*@[a-z0-9-]+(\.[a-z0-9-]+)*(\.[a-z]{2,4})$')
        #general_link_validation = re.compile(r'')
        #We stored already crawled links in this list
        crawledLinks    = set()
        titles = sel.xpath('//div[@id="content"]//h1[@id="firstHeading"]//span/text()').extract()
        contents = sel.xpath('//body/div[@id="content"]').extract()
        if contents:
            content = contents[0]
        if titles: 
            title = titles[0]
        else:
            return
        links   = sel.xpath('//a/@href').extract()


        for link in links:
            # If it is a proper link and is not checked yet, yield it to the Spider
            url = urljoin(response.url, link)
            #print url
            ## our url must not have any ":" character in it. link /wiki/talk:company
            if not url in crawledLinks and re.match(r'http://en.wikipedia.org/wiki/[^:]+$', url):
                crawledLinks.add(url)
                  #print url, depth
                yield Request(url, self.parse)
        item = MainItem()
        item["title"] = title
        print '*'*80
        print 'crawled: %s | it has %s links.' % (title, len(links))
        #print content
        print '*'*80
        item["links"] = list(crawledLinks)
        writer.add_document(title=title, content=nltk.clean_html(content))  ## I save only text from content.
        #print crawledLinks
        writer.commit()
        yield item