直播课爬虫代码

'''爬虫阿铭linux教程，保存为本地的pdf文件'''

import re

import os

import pdfkit
import requests


if not os.path.exists("aminglinux"):
    os.mkdir("aminglinux")
os.chdir("aminglinux")

url = "http://www.apelearn.com/study_v2/"
s = requests.session()
text = s.get(url).text
print(text)
reg = re.compile(r'
.*
')
result = reg.findall(text)
res = list(set(result))
pdfUrl = "http://www.apelearn.com/study_v2/"
for i in res:
    url = "{0}{1}".format(pdfUrl, i)
    pdfFileName = i.replace("html", "pdf")
    print(pdfFileName)
    try:
        pdfkit.from_url(url, pdfFileName)
    except:
        continue