我对Python相当陌生，我不知道selenium是什么，但是如果您能够找到某种模式，您应该能够执行您描述的内容。关键是找到一个模式。下面是几个示例脚本，它们可能会让您了解如何开始。在import urllib2

from bs4 import BeautifulSoup

f = open('C:/Users/rshuell001/Desktop/test.txt', 'w')

link = "http://espn.go.com/nba/team/roster/_/name/bkn/brooklyn-nets"

page = urllib2.urlopen(link)

soup = BeautifulSoup(page, "html.parser")

table = soup.find("table")

for row in table.findAll("tr",{"class":["oddrow","evenrow"]}):

col = row.findAll('td')

player = col[1].string

position = col[2].string

f.write(player + '\t' + position + '\n')

f.close()

******** ******** ******** ******** ******** ******** ******** ******** ******** ********

from bs4 import BeautifulSoup

from urllib2 import urlopen

def make_soup(url):

html = urlopen(url).read()

return BeautifulSoup(html)

def get_teams():

url = "http://espn.go.com/nba/teams"

soup = make_soup(url)

teams = []

for team_chunk in soup.find_all('ul', class_='medium-logos'):

li_tags = team_chunk.find_all('li')

for li in li_tags:

team = li.h5.a

link = team['href']

teams.append(link.encode('utf-8'))

return teams

if __name__ == "__main__":

print get_teams()

print len(get_teams())

import requests

from bs4 import BeautifulSoup

r = requests.get("http://www.kijiji.ca/h-gander/1700255")

soup = BeautifulSoup(r.content)

print soup.find_all("a",{"class":"category-selected"})

import requests

from bs4 import BeautifulSoup

url = "http://www.indeed.com/jobs?q=hardware+engineer&l=San+Francisco%2C+CA"

r = requests.get(url)

soup = BeautifulSoup(r.content)

job_titles = soup.find_all("h2", {"class", "jobtitle"})

for job in job_titles:

print job.text.strip()