Question

我正在尝试在Linux中运行此python代码（第二天同时使用linux和python）我从github复制了该程序，并且需要更改标头，因为我使用的服务器使用Firefox 60.2.2，我正尝试收集网络上的图像并将其保存到文件中。但是，我收到HTTP错误400：错误的请求。如果您有任何解决方案，请解释一下，因为我是该程序的新手。

代码：

  #!/usr/bin/env python
    import os
    import urllib.request as ulib
    from bs4 import BeautifulSoup as Soup
    import json

    url_a = 'https://www.google.com/search?ei=1m7NWePfFYaGmQG51q7IBg&hl=en&q={}'
    url_b = '\&tbm=isch&ved=0ahUKEwjjovnD7sjWAhUGQyYKHTmrC2kQuT0I7gEoAQ&start={}'
    url_c = '\&yv=2&vet=10ahUKEwjjovnD7sjWAhUGQyYKHTmrC2kQuT0I7gEoAQ.1m7NWePfFYaGmQG51q7IBg'
    url_d = '\.i&ijn=1&asearch=ichunk&async=_id:rg_s,_pms:s'
    url_base = ''.join((url_a, url_b, url_c, url_d))

    headers = {'User-Agent':'Mozilla/5.0 (X11; Linux i986; rv:60.0) Gecko/20200101 Firefox/60.0'}


    def get_links(search_name):
        search_name = search_name.replace(' ', '+')
        url = url_base.format(search_name, 0)
        request = ulib.Request(url, None, headers)
        json_string = ulib.urlopen(request).read()
        page = json.loads(json_string)
        new_soup = Soup(page[1][1], 'lxml')
        images = new_soup.find_all('img')
        links = [image['src'] for image in images]
        return links


    def save_images(links, search_name):
        directory = search_name.replace(' ', '_')
        if not os.path.isdir(directory):
            os.mkdir(directory)

        for i, link in enumerate(links):
            savepath = os.path.join(directory, '{:06}.png'.format(i))
            ulib.urlretrieve(link, savepath)


    if __name__ == '__main__':
        search_name = 'auv side scan sonar sunken ship'
        links = get_links(search_name)
        save_images(links, search_name)

(tensorflow) [usr-login2 darkflow-master]$ ./get_jimages.py
Traceback (most recent call last):
  File "./get_jimages.py", line 40, in <module>
    links = get_links(search_name)
  File "./get_jimages.py", line 20, in get_links
    json_string = ulib.urlopen(request).read()
  File "/home/usr/anaconda3/envs/tensorflow/lib/python3.6/urllib/request.py", line 223, in urlopen
    return opener.open(url, data, timeout)
  File "/home/usr/anaconda3/envs/tensorflow/lib/python3.6/urllib/request.py", line 532, in open
    response = meth(req, response)
  File "/home/usr/anaconda3/envs/tensorflow/lib/python3.6/urllib/request.py", line 642, in http_response
    'http', request, response, code, msg, hdrs)
  File "/home/usr/anaconda3/envs/tensorflow/lib/python3.6/urllib/request.py", line 570, in error
    return self._call_chain(*args)
  File "/home/usr/anaconda3/envs/tensorflow/lib/python3.6/urllib/request.py", line 504, in _call_chain
    result = func(*args)
  File "/home/usr/anaconda3/envs/tensorflow/lib/python3.6/urllib/request.py", line 650, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 400: Bad Request

如何使用Linux服务器修复HTTP错误400：错误的请求？

0 个答案: