pythonは簡単な爬虫類検索機能を実現します

1756 ワード

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 = url
        response = urlopen(url)
        if response.getheader('Content-Type')=='text/html; charset=UTF-8':
            htmlBytes = response.read()
            htmlString = htmlBytes.decode("utf-8")
            self.feed(htmlString)
            return htmlString, self.links
        else:
            return "",[]

def spider(url, word, maxPages):  
    pagesToVisit = [url]
    numberVisited = 0
    foundWord = 4
    while numberVisited < maxPages and pagesToVisit != [] and not foundWord:
        numberVisited = numberVisited +1
        url = pagesToVisit[0]
        pagesToVisit = pagesToVisit[1:]
        try:
            print(numberVisited, " :", url)
            parser = LinkParser()
            data, links = parser.getLinks(url)
            #print("data:",links)
            pagesToVisit = pagesToVisit + links
            if data.find(word)>-1:
                foundWord = True
                pagesToVisit = pagesToVisit + links
                print(" ** !**")
        except:
            print(" ** !**")
    if foundWord:
        print(" ", word, " ", url)
    else:
        print(" ")
spider("http://yuedu.fm/"," ",100)