python - 无法将下载的文件存储在相关文件夹中

Question

我用 python 结合 selenium 编写了一个脚本，用于从网页下载几个文档文件(以 .doc 结尾)。我不想使用 requests 或 urllib 模块下载文件的原因是因为我目前正在使用的网站没有任何真实的 url 连接到每个文件.它们是 javascript 加密的。但是，我在我的脚本中选择了一个链接来模仿它。

此时我的脚本做了什么:

1. 在桌面创建一个主文件夹
2. 使用要下载的文件的名称在主文件夹中创建子文件夹
3. 下载文件开始点击他们的链接并将文件放在主文件夹中。 (这是我需要纠正的)

How can I modify my script to download the files initiating click on their links and put the downloaded files in their concerning folders?

这是我目前的尝试:

import os
import time
from selenium import webdriver

link ='https://www.online-convert.com/file-format/doc' 

dirf = os.path.expanduser('~')
desk_location = dirf + r'\Desktop\file_folder'
if not os.path.exists(desk_location):os.mkdir(desk_location)

def download_files():
    driver.get(link)
    for item in driver.find_elements_by_css_selector("a[href$='.doc']")[:2]:
        filename = item.get_attribute("href").split("/")[-1]
        #creating new folder in accordance with filename to store the downloaded file in thier concerning folder
        folder_name = item.get_attribute("href").split("/")[-1].split(".")[0]
        #set the new location of the folders to be created
        new_location = os.path.join(desk_location,folder_name)
        if not os.path.exists(new_location):os.mkdir(new_location)
        #set the location of the folders the downloaded files will be within
        file_location = os.path.join(new_location,filename)
        item.click()

        time_to_wait = 10
        time_counter = 0
        try:
            while not os.path.exists(file_location):
                time.sleep(1)
                time_counter += 1
                if time_counter > time_to_wait:break
        except Exception:pass

if __name__ == '__main__':
    chromeOptions = webdriver.ChromeOptions()
    prefs = {'download.default_directory' : desk_location,
            'profile.default_content_setting_values.automatic_downloads': 1
        }
    chromeOptions.add_experimental_option('prefs', prefs)
    driver = webdriver.Chrome(chrome_options=chromeOptions)
    download_files()

下图表示下载文件当前的存储方式(文件在其相关文件夹之外):

Answer 1

我只是添加了文件的重命名来移动它。所以它会像你拥有的那样工作，但是一旦它下载了文件，就会将它移动到正确的路径:

os.rename(desk_location + '\\' + filename, file_location)

完整代码:

import os
import time
from selenium import webdriver

link ='https://www.online-convert.com/file-format/doc' 

dirf = os.path.expanduser('~')
desk_location = dirf + r'\Desktop\file_folder'
if not os.path.exists(desk_location):
    os.mkdir(desk_location)

def download_files():
    driver.get(link)
    for item in driver.find_elements_by_css_selector("a[href$='.doc']")[:2]:
        filename = item.get_attribute("href").split("/")[-1]
        #creating new folder in accordance with filename to store the downloaded file in thier concerning folder
        folder_name = item.get_attribute("href").split("/")[-1].split(".")[0]
        #set the new location of the folders to be created
        new_location = os.path.join(desk_location,folder_name)
        if not os.path.exists(new_location):
            os.mkdir(new_location)
        #set the location of the folders the downloaded files will be within
        file_location = os.path.join(new_location,filename)
        item.click()

        time_to_wait = 10
        time_counter = 0

        try:
            while not os.path.exists(file_location):
                time.sleep(1)
                time_counter += 1
                if time_counter > time_to_wait:break
            os.rename(desk_location + '\\' + filename, file_location)
        except Exception:pass

if __name__ == '__main__':
    chromeOptions = webdriver.ChromeOptions()
    prefs = {'download.default_directory' : desk_location,
            'profile.default_content_setting_values.automatic_downloads': 1
        }
    chromeOptions.add_experimental_option('prefs', prefs)
    driver = webdriver.Chrome(chrome_options=chromeOptions)
    download_files()