#

from bs4 import BeautifulSoupfrom urllib.request import urlopenres = urlopen('http://pythonscraping.com/pages/page1.html')bs = BeautifulSoup(res.read(),'html.parser')print(bs.h1)  #获取标签内容

from urllib.request import urlopenfrom urllib.error import HTTPErrorfrom bs4 import BeautifulSoupimport sysdef getTitle(url):    try:        html = urlopen(url)    except HTTPError as e:        print(e)        return None    try:        bsObj = BeautifulSoup(html, "html.parser")        title = bsObj.body.h1    except AttributeError as e:        return None    return titletitle = getTitle("http://www.pythonscraping.com/exercises/exercise1.html")if title == None:    print("Title could not be found")else:    print(title)

from urllib.request import urlopenfrom bs4 import BeautifulSoupimport datetimeimport randomimport rerandom.seed(datetime.datetime.now())#随机数种子  时间种子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"]    print(newArticle)    links = getLinks(newArticle)

Natural Language Toolkit，自然语言处理工具包，在NLP领域中，最常使用的一个Python库