Py无处不在，你真的感受到了？

# 复制n行
nyy  例如复制10行 10yy 
# 粘贴
p

import os
def file_name(file_dir):
    file_list = []
    # 三元tupple(dirpath, dirnames, filenames)
    '''
    dirpath：string，代表目录的路径；
    dirnames：list，包含了当前dirpath路径下所有的子目录名字（不包含目录路径）；
    filenames：list，包含了当前dirpath路径下所有的非目录子文件的名字（不包含目录路径）。
    '''
    for root, dirs, files in os.walk(file_dir):
        print(root)
        print(dirs)
        print("----")
        print(files)
        for file in files:
            print(os.path.splitext(file))
            if os.path.splitext(file)[1] == '.md':
                file_list.append(os.path.join(root, file))
    return file_list

def md_Link(file_list):
    for file in file_list:
        with open(file, 'r+', encoding='utf-8') as f:
            d = f.read()
            t = d.replace('http://xxxx.clouddn.com', 'https://raw.githubusercontent.com/xxxx/xxxx/xxx')
            f.seek(0, 0)
            f.write(t)

import requests
from urllib import request
from lxml import etree
import os
import re
import time

base_url = 'http://cs231n.stanford.edu/slides/'

class slides_Spider:
    def __init__(self):
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
        }
        self.headers = headers

def get_Html(self,url):
    html = requests.get(url, headers=self.headers).text
    selector = etree.HTML(html)
    return selector

['2015/', '2016/', '2017/', '2018/']
['http://xxx/2015/', 'http://xxx/slides/2016/', ...]

def get_yearUrl(self,url):
    selector = self.get_Html(url)
    year_Href=selector.xpath('//a[starts-with(@href, "20")]/text()')
    # 得到每个url的text，为一个list
    print(year_Href)
    year_sildeHref = []
    # 每个url拼接，得到跳转年份的url
    for i in range(len(year_Href)):
        year_sildeHref.append(base_url+year_Href[i])
    print(year_sildeHref)
    return year_Href,year_sildeHref

{'2015': ['http://xxx/2015/xxx.pdf'...],'2016':[.....].....}

def get_AllUrl(self,url):
    year_Href,year_sildeHref = self.get_yearUrl(url)
    pdf_dict = {}
    for i in range(len(year_sildeHref)):
        pdf_list = []
        selector = self.get_Html(year_sildeHref[i])
        pdf_response = selector.xpath('//a[contains(@href,"pdf")]/text()')
         # 去掉2015后面的/
        year_Href[i] = year_Href[i].replace('/','')
        for j in pdf_response:
            pdf_list.append(year_sildeHref[i]+j)
        pdf_dict[year_Href[i]] = pdf_list

    print(pdf_dict)
    return pdf_dict

def downLoad_Pdf(self,url):
    pdf_dict = self.get_AllUrl(url)
    for key in pdf_dict:
        path = key
        if not os.path.exists(path):
            os.mkdir(path)
        else:
            print("目录已存在")
        print("---------"+ key +"年资料正在下载---------")
        for each in pdf_dict[key]:
            pdf_name = re.split('/', each)[-1]
            print(pdf_name)
            content = requests.get(each,headers=self.headers)
            with open(path+'/'+pdf_name, 'wb') as f:
                for chunk in content.iter_content(chunk_size=32):
                    f.write(chunk)
            time.sleep(2)
        print("---------" + key + "年资料下载完毕---------")
    print("---------下载完毕---------")

s = slides_Spider()
allPdf_url = s.downLoad_Pdf(base_url)
print(allPdf_url)