python网络数据采集6 打印标题，正文，编辑链接

[python]代码库

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()) # 打印标题
        print(bsObj.find(id="mw-content-text").findAll('p')[0]) # 打印正文
        print(bsObj.find(id="ca-edit").find("span").find("a").attrs['href']) # 打印编辑链接
    except AttributeError:
        print("页面缺少一些属性！不过不用担心！")

    for link in bsObj.findAll("a", href=re.compile("^(/wiki/)")):
        if 'href' in link.attrs:
            if link.attrs['href'] not in pages:
                newPage = link.attrs['href']
                print("--------------\n"+newPage)
                pages.add(newPage)
                getLinks(newPage)

getLinks("")

[代码运行效果截图]