Question

一切都可以在我的计算机上进行。我将文件上传到服务器上，并且错误不断。在下载第一个图像时停止处理。

目标路径'/home/matms/django_project/media_root/xxx.jpg' 已经存在

 def scrape(request):
        filelist = glob.glob(os.path.join("/home/matms/django_project/media_root", "*.jpg"))
        for f in filelist:
            os.remove(f)

        old_articles = Weather.objects.all()
        old_articles.delete()
        user_prof = UserProfile.objects.filter(user=request.user).first()
        if user_prof is not None:
            user_prof.last_scrape = datetime.now(timezone.utc)
            user_prof.save()

        session = requests.Session()
        session.headers = { 
           "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/"}
        url = 'https://www.onet.pl/'

        content = session.get(url, verify=False).content

        soup = BeautifulSoup(content, "html.parser")
        posts = soup.find_all('div', {'class': 'sectionLine'})

        for post in posts:
            title = post.find('span', {'class': 'title'}).get_text()
            link = post.find("a")['href']
            image_source = post.find('img')['src']
            image_source_solved = "http:{}".format(image_source)

            media_root = '/home/matms/django_project/media_root'
            if not image_source_solved.startswith(("data:image", "javascript")):
                #exists = os.path.isfile(media_root+image_source_solved)
                exists = 1
                if exists == 2:
                    pass
                else:
                    local_filename = image_source_solved.split('/')[-1].split("?")[0]+".jpg"
                    r = session.get(image_source_solved, stream=True, verify=False)
                    with open(os.path.join(settings.MEDIA_ROOT, local_filename), 'wb') as f:
                        for chunk in r.iter_content(chunk_size=1024):
                            f.write(chunk)

                    current_image_absolute_path = os.path.abspath(local_filename)
                    shutil.move(current_image_absolute_path, media_root)

                new_headline = Headline()
                new_headline.title = title
                new_headline.url = link
                new_headline.image = local_filename
                new_headline.save()
                sleep(1)

错误日志：

>     [Thu Sep 26 10:07:31.560075 2019] [wsgi:error] [pid 10690:tid 140110581073664] [remote 89.78.216.206:56770]   File
> "/home/matms/django_project/news/views.py", line 102, in scrape
>     [Thu Sep 26 10:07:31.560078 2019] [wsgi:error] [pid 10690:tid 140110581073664] [remote 89.78.216.206:56770]    
> shutil.move(current_image_absolute_path, media_root)

Answer 1

您正在将文件写入settings.MEDIA_ROOT / local_filename，然后将其移动到media_root。

显然，您的服务器上的settings.MEDIA_ROOT和media_root是相同的，所以shutil.move抱怨该文件已经存在。

目标路径'/home/matms/django_project/media_root/xxx.jpg'已经存在

1 个答案: