python网络爬虫（慕课网）

代码：

##爬取网络：慕课网（"

from bs4 import BeautifulSoup

import urllib.request

import xlwt

import time

time_star = time.time()

ur = ["mobile","python","java","php"] ##通过查看网页源代码，手动构造访问链接

url_basic, mingc, lianj, url, hda, x = [], [], [], [], [], 1

for j in range(len(ur)):

url_basic.append("

for i in range(7): ##网页个数最多为7

urll = url_basic[j] + str(i)

url.append(urll)

heads = {

'Connection': 'keep-alive',

'Accept-Language': 'zh-CN,zh;q=0.9',

'Accept': 'text/html,application/xhtml+xml,application/xml;\

q=0.9,image/webp,image/apng,*/*;q=0.8',

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36\

(KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',

}

for key,value in heads.items():

items = (key,value)

hda.append(items)

opn = urllib.request.build_opener()

opn.addheaders = hda

urllib.request.install_opener(opn)

for i in url:

tr