Web Crawler - JaeWan Pro
Posted by JanWan
Last Updated: February 24, 2017
# We are going to create a class called LinkParser that inherits some
# methods from HTMLParser which is why it is passed into the definition

from html.parser import HTMLParser
from urllib.request import urlopen
from urllib import parse

class LinkParser(HTMLParser):
	def handle_starttag(self, tag, attrs):
		if tag == 'a':
			for(key, value) in attrs:
				if key == 'href':
					newUrl = parse.urljoin(self.baseUrl, value)
					self.links = self.links + [newUrl]
	def getLinks(self, url):
		self.links = []
		self.baseUrl = urlresponse = urlopen(url)
		if response.getheader('Content-Type') == 'text/html':
			htmlBytes = response.read()
			htmlString = htmlBytes.decode("utf-8")
			return htmlString, self.links
			return "",[]
def spider(url, word, maxPages):
	pagesToVisit = [url]
	numberVisited = 0
	foundWord = False
	while numberVisited < maxPages and pagesToVisit != [] and not foundWord:
		numberVisited = numberVisited +1
		url = pagesToVisit[0]
		pagesToVisit = pagesToVisit[1:]
                        print(numberVisited, "Visiting:", url)
			parser = LinkParser()
			data, links = parser.getLinks(url)
			if data.find(word) > -1:
				found = True
			pagesToVisit = pagesToVisit + links
	if foundWord:
		print("The word", word, "was found at", url)
		print("Word never found")


Related Content