循环获取链接

from urllib.request import urlopen
from urllib.error import HTTPError
from urllib.error import URLError
from bs4 import BeautifulSoup
import random
import datetime
import re

pages = set()
random.seed(datetime.datetime.now())

def getInternalLinks(bsObject,includeUrl):
        internalLinks = []
        for link in bsObject.findAll('a',href = re.compile('^(/|.{0,2}' + includeUrl + ')')):
                if link.attrs['href'] is not None:
                        href = 'http://' + re.sub('^(.|/)+','',link.attrs['href'])
                        if href not in internalLinks:
                                internalLinks.append(href)
        return(internalLinks)

def splitAddress(address):
    addressParts = address.replace('http://','').split('/')
    return(addressParts)

def getExternalLinks(bsObject,excludeUrl):
    externalLinks = []
    for link in bsObject.findAll('a',{'href': re.compile('^(http)((?!' + excludeUrl + ').)*$')}):
        if link.attrs['href'] is not None:
            href = link.attrs['href']
            if href not in externalLinks:
                externalLinks.append(href)
    return(externalLinks)

def getRandomExternalLink(startingPage):
        html = urlopen(startingPage)
        bsObject = BeautifulSoup(html,'html.parser')
        externalLinks = getExternalLinks(bsObject,splitAddress(startingPage)[0])
        if len(externalLinks) == 0:
                internalLinks = getInternalLinks(bsObject,splitAddress(startingPage)[0])
                return(getRandomExternalLink(internalLinks[random.randint(0,len(internalLinks) - 1)]))
        else:
                return(externalLinks[random.randint(0,len(externalLinks) - 1)])

def followExternalOnly(startingSite):
        externalLink = getRandomExternalLink(startingSite)
        print('随机外链是: ' + externalLink)
        try:
            followExternalOnly(externalLink)
        except (HTTPError,ValueError,URLError):
            followExternalOnly(startingSite)

followExternalOnly('http://www.baidu.com/')