pdf和doc用python下载和文档特定关键词筛选

参考文章链接在这儿，感谢（没有列出的我会仔细找一下列出来）

http://python3-cookbook.readthedocs.io/zh_CN/latest/c13/p07_copy_move_files_and_directories.html

https://www.liaoxuefeng.com/wiki/0014316089557264a6b348958f449949df42a6d3a2e542c000/0014316724772904521142196b74a3f8abf93d8e97c6ee6000

这是我的GitHub地址：https://github.com/NieShengyuan/pythonSpider/tree/master/PDF_Download

这是文档下载程序

包括：URL解析，requests方法，文档命名保存

# _*_ coding:utf-8_*_
# auther :nsy12
# date   :2018/2/25 
# time   :11:20

import requests
import re, os
from bs4 import BeautifulSoup
import time
import random

global NUM

url_datas = [
    'https://**.cn',
    'https://.cn',
    'https://.cn',
    'https://.cn',
    'https://.cn'
]


def download(url, pdf_name, dir):
    '''
    判断文件是否存在，若不存在则下载，需要在程序启动前获取文件列表
    :param url: 指向文档的URL
    :param pdf_name: 文档名称
    :param dir: 保存地址
    :return:
    '''
    # showPdf(url, pdf_name)
    # 判断文件是否存在
    if pdf_name in files:
        print(pdf_name + '  exist')
    else:
        response = requests.get(url, data=None, stream=True)
        if not os.path.exists(dir):
            os.makedirs(dir)
        with open(os.path.join(dir, pdf_name), "wb") as pdf_file:
            for content in response.iter_content():
                pdf_file.write(content)
        print("    " + pdf_name + " has been downloaded!!")


def get_urls(url, dir):
    '''
    对URL指向的网站进行解析，获取文档链接
    :param url: 需解析的URL
    :param dir: 文档保存路径
    :return:
    '''
    print("Please wait for second ...")
    global NUM
    html = requests.get(url, data=None)
    # html.encoding = 'utf-8'  # 指定网页编码方式（查看网页源代码）
    # print(html.encoding)
    # print(html.status_code)
    # print(html.text)

    soup = BeautifulSoup(html.text, 'lxml')
    # all_a = soup.find('div', class_='cvideotitle').find_all('a')
    all_a = soup.find('div').find_all('a')
    for a in all_a:
        title = a.get_text()
        url_pdf = a['href']
        name = title[19:-18]

        print(str(NUM) + '       开始保存：' + name)
        NUM = NUM + 1
        download(url_pdf, str(name), dir)
        # time.sleep(random.randint(1, 2))

        """
        #将数据写入记事本
        # with open(r'D:jishubaogao\date.txt', 'a', encoding='gbk') as f:
            f.write(name + '\n')
        """


if __name__ == "__main__":
    global NUM
    FILE_DIR = r'E:\\1smart Car\paper\Twelfth'
    files = os.listdir(FILE_DIR)  # 读取文件夹下存在的文件

    NUM = 1
    for url_data in url_datas:
        get_urls(url_data, FILE_DIR)
        print("finsh" + url_data)

    print("             finsh download")

下面是文档特定关键词筛选，并复制进特定地址

包括：文件夹下所有文件名获取，对特定关键词筛选，复制进特定路径的方法

# _*_ coding:utf-8_*_
# auther :nsy12
# date   :2018/2/28 
# time   :16:25
# 筛选关键字，并将文件分类保存
import os
import shutil

global NUM, RESULT


def name_analyze(sub, dir):
    '''
    :param sub: 待筛选字符串
    :param dir: 待保存地址
    :return:
    '''
    global RESULT
    # 筛选关键词
    result1 = sub.find('双车')
    result2 = sub.find('追逐')

    if result1 == -1:
        result1 = 0
    if result2 == -1:
        result2 = 0
    # 筛选条件
    if (result1 or result2) != 0:
        # 操作函数
        fileClassify(sub, dir)
        RESULT += 1
        print('   exist' + str(sub))


def fileClassify(fileName, dir):
    '''
    :param fileName:待移动文件名
    :param dir: 待移动新地址
    :return:
    '''
    # 创建文件夹
    if not os.path.exists(dir):
        os.makedirs(dir)
    filesDirs = os.listdir(dir)
    # 查重
    if fileName in filesDirs:
        print(fileName + '  exist')
    else:
        shutil.copy(DIR_PATH + '/' + str(fileName), dir)  # ("oldpos", "newpos")  # 移动文件或目录
        print("    " + fileName + " has been moved!!")


if __name__ == "__main__":
    global NUM, RESULT
    NUM = 1
    RESULT = 1
    # 待筛选地址
    DIR_PATH = 'E:\\1smart Car\paper\Twelfth'
    # 待保存地址
    NEW_DIR = 'E:\\1smart Car\paper\sc'
    files = os.listdir(DIR_PATH)

    for file in files:
        name_analyze(file, NEW_DIR)
        NUM += 1
        print(NUM)

    print("共计" + str(RESULT) + "个结果")