python爬虫: 从 指定路径 爬取 文件

    # 替换为你指定的 url
    url = 'https://... ...'

python spider.py

# coding=utf-8
import os
import urllib
import logging
import sys

# logging配置
logging.basicConfig(
    format='%(asctime)s %(levelname)s %(message)s',
    level=logging.INFO,
    stream=sys.stdout)

file_path = os.path.join(os.getcwd(),'dir_name/file_name')

if not os.path.isfile(file_path):
    logging.info("File doesn't exist.")
    # 替换为你指定的 url
    url = 'https://... ...'

    # 一旦用于存放下载文件的 本地目录：'dir_name/' 不存在
    file_dir = file_path[:-9]
    if not os.path.exists(file_dir):
        logging.info("Mkdir 'dir_name/'.")
        os.mkdir(file_dir)

    def down(_save_path, _url):
        try:
            urllib.urlretrieve(_url, _save_path)
        except:
            print '\nError when retrieving the URL:', _save_path

    logging.info("Downloading file.")
    down(file_path, url)
else:
    logging.info("File exists.")