PythonクローラーパッケージBeautifulSoupの再帰的クローリング例の詳細説明

# -*- coding: utf-8 -*-
# @Author: HaonanWu
# @Date:  2016-12-25 10:35:00
# @Last Modified by:  HaonanWu
# @Last Modified time: 2016-12-25 10:52:26
from urllib2 import urlopen
from bs4 import BeautifulSoup
 
html = urlopen('http://en.wikipedia.org/wiki/Kevin_Bacon')
bsObj = BeautifulSoup(html, "html.parser")
 
for link in bsObj.findAll("a"):
  if 'href' in link.attrs:
    print link.attrs['href']

/wiki/Wikipedia:Protection_policy#semi
#mw-head
#p-search
/wiki/Kevin_Bacon_(disambiguation)
/wiki/File:Kevin_Bacon_SDCC_2014.jpg
/wiki/San_Diego_Comic-Con
/wiki/Philadelphia
/wiki/Pennsylvania
/wiki/Kyra_Sedgwick

from urllib2 import urlopen
from bs4 import BeautifulSoup
import datetime
import random
import re
 
pages = set()
random.seed(datetime.datetime.now())
def getLinks(articleUrl):
  html = urlopen("http://en.wikipedia.org"+articleUrl)
  bsObj = BeautifulSoup(html, "html.parser")
  return bsObj.find("div", {"id":"bodyContent"}).findAll("a", href=re.compile("^(/wiki/)((?!:).)*$"))
 
links = getLinks("/wiki/Kevin_Bacon")
while len(links) > 0:
  newArticle = links[random.randint(0, len(links)-1)].attrs["href"]
  if newArticle not in pages:
    print(newArticle)
    pages.add(newArticle)
    links = getLinks(newArticle)

from urllib.request import urlopen
from bs4 import BeautifulSoup
import re
 
pages = set()
def getLinks(pageUrl):
  global pages
  html = urlopen("http://en.wikipedia.org"+pageUrl)
  bsObj = BeautifulSoup(html, "html.parser")
  try:
    print(bsObj.h1.get_text())
    print(bsObj.find(id ="mw-content-text").findAll("p")[0])
    print(bsObj.find(id="ca-edit").find("span").find("a").attrs['href'])
  except AttributeError:
    print("This page is missing something! No worries though!")
 
  for link in bsObj.findAll("a", href=re.compile("^(/wiki/)")):
    if 'href' in link.attrs:
      if link.attrs['href'] not in pages:
        #We have encountered a new page
        newPage = link.attrs['href']
        print("----------------\n"+newPage)
        pages.add(newPage)
        getLinks(newPage)
getLinks("")