PyG导入GemsecDeezer：urllib.error.HTTPError: HTTP Error 404: Not Found

本文链接：https://blog.youkuaiyun.com/Cyril_KI/article/details/126191113

在尝试使用PyG加载GemsecDeezer数据集时遇到404错误。问题源于URL中存在不正确的路径分隔符。通过检查源代码并替换URL中的``为`/`，解决了HTTP 404 Not Found的问题。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

场景

使用PyG导入GemsecDeezer：

dataset = GemsecDeezer(root='data/GemsecDeezer', name='HU')

报错代码

Downloading https://graphmining.ai/datasets/ptg/gemsec\HU.npz
https://graphmining.ai/datasets/ptg/gemsec\HU.npz
Traceback (most recent call last):
  File "test.py", line 22, in <module>
    dataset = GemsecDeezer(root='data/GemsecDeezer', name='HU')
  File "F:\Anaconda3\lib\site-packages\torch_geometric\datasets\gemsec.py", line 40, in __init__
    super().__init__(root, transform, pre_transform)
  File "F:\Anaconda3\lib\site-packages\torch_geometric\data\in_memory_dataset.py", line 57, in __init__
    super().__init__(root, transform, pre_transform, pre_filter)
  File "F:\Anaconda3\lib\site-packages\torch_geometric\data\dataset.py", line 85, in __init__
    self._download()
  File "F:\Anaconda3\lib\site-packages\torch_geometric\data\dataset.py", line 146, in _download
    self.download()
  File "F:\Anaconda3\lib\site-packages\torch_geometric\datasets\gemsec.py", line 60, in download
    download_url(osp.join(self.url, self.name + '.npz'), self.raw_dir)
  File "F:\Anaconda3\lib\site-packages\torch_geometric\data\download.py", line 35, in download_url
    data = urllib.request.urlopen(url, context=context)
  File "F:\Anaconda3\lib\urllib\request.py", line 222, in urlopen
    return opener.open(url, data, timeout)
  File "F:\Anaconda3\lib\urllib\request.py", line 531, in open
    response = meth(req, response)
  File "F:\Anaconda3\lib\urllib\request.py", line 641, in http_response
    'http', request, response, code, msg, hdrs)
  File "F:\Anaconda3\lib\urllib\request.py", line 569, in error
    return self._call_chain(*args)
  File "F:\Anaconda3\lib\urllib\request.py", line 503, in _call_chain
    result = func(*args)
  File "F:\Anaconda3\lib\urllib\request.py", line 649, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 404: Not Found

Process finished with exit code 1

解决

代码提示url不存在，查看PyG中源码：

def download(self):
    download_url(osp.join(self.url, self.name + '.npz'), self.raw_dir)

输出url：

print(osp.join(self.url, self.name + '.npz'))
https://graphmining.ai/datasets/ptg/gemsec\HU.npz

将url中的\换成/即可：

def download(self):
    download_url(osp.join(self.url, self.name + '.npz').replace('\\', '/'), self.raw_dir)