Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

爬虫代码出现下列报错 #5

Open
yangyangk99 opened this issue May 24, 2023 · 0 comments
Open

爬虫代码出现下列报错 #5

yangyangk99 opened this issue May 24, 2023 · 0 comments

Comments

@yangyangk99
Copy link

2023-05-24 15:44:49 [scrapy.core.scraper] ERROR: Error downloading <GET https://zh.wikipedia.org/wiki/%E8%A1%8C%E7%A8%8B>
Traceback (most recent call last):
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/cache.py", line 190, in run_and_cache
result = self.get(namespace=namespace, key=key_args)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/cache.py", line 93, in get
raise KeyError("namespace: " + namespace + " key: " + repr(key))
KeyError: "namespace: publicsuffix.org-tlds key: {'urls': ('https://publicsuffix.org/list/public_suffix_list.dat', 'https://raw.githubusercontent.com/publicsuffix/list/master/public_suffix_list.dat'), 'fallback_to_snapshot': True}"

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/cache.py", line 190, in run_and_cache
result = self.get(namespace=namespace, key=key_args)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/cache.py", line 93, in get
raise KeyError("namespace: " + namespace + " key: " + repr(key))
KeyError: "namespace: urls key: {'url': 'https://publicsuffix.org/list/public_suffix_list.dat'}"

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/twisted/internet/defer.py", line 1697, in _inlineCallbacks
result = context.run(gen.send, result)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/scrapy/core/downloader/middleware.py", line 64, in process_response
method(request=request, response=response, spider=spider)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/scrapy/downloadermiddlewares/cookies.py", line 73, in process_response
self._process_cookies(cookies, jar=jar, request=request)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/scrapy/downloadermiddlewares/cookies.py", line 44, in _process_cookies
if cookie_domain and _is_public_domain(cookie_domain):
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/scrapy/downloadermiddlewares/cookies.py", line 19, in _is_public_domain
parts = _split_domain(domain)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/tldextract.py", line 233, in call
suffix_index = self._get_tld_extractor().suffix_index(
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/tldextract.py", line 274, in _get_tld_extractor
public_tlds, private_tlds = get_suffix_lists(
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/suffix_list.py", line 55, in get_suffix_lists
return cache.run_and_cache(
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/cache.py", line 192, in run_and_cache
result = func(**kwargs)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/suffix_list.py", line 72, in _get_suffix_lists
text = find_first_response(cache, urls, cache_fetch_timeout=cache_fetch_timeout)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/suffix_list.py", line 30, in find_first_response
return cache.cached_fetch_url(
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/cache.py", line 199, in cached_fetch_url
return self.run_and_cache(
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/cache.py", line 192, in run_and_cache
result = func(**kwargs)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/tldextract/cache.py", line 209, in _fetch_url
response = session.get(url, timeout=timeout)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/requests/sessions.py", line 600, in get
return self.request("GET", url, **kwargs)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/requests/sessions.py", line 587, in request
resp = self.send(prep, **send_kwargs)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/requests/sessions.py", line 701, in send
r = adapter.send(request, **kwargs)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/requests/adapters.py", line 455, in send
conn = self.get_connection(request.url, proxies)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/requests/adapters.py", line 352, in get_connection
conn = proxy_manager.connection_from_url(url)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/urllib3/poolmanager.py", line 299, in connection_from_url
return self.connection_from_host(
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/urllib3/poolmanager.py", line 500, in connection_from_host
return super(ProxyManager, self).connection_from_host(
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/urllib3/poolmanager.py", line 246, in connection_from_host
return self.connection_from_context(request_context)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/urllib3/poolmanager.py", line 261, in connection_from_context
return self.connection_from_pool_key(pool_key, request_context=request_context)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/urllib3/poolmanager.py", line 282, in connection_from_pool_key
pool = self._new_pool(scheme, host, port, request_context=request_context)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/urllib3/poolmanager.py", line 214, in _new_pool
return pool_cls(host, port, **request_context)
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/urllib3/connectionpool.py", line 938, in init
HTTPConnectionPool.init(
File "/Users/luhongyang/opt/anaconda3/python.app/Contents/lib/python3.9/site-packages/urllib3/connectionpool.py", line 198, in init
self.pool = self.QueueCls(maxsize)
TypeError: LifoQueue() takes no arguments

报错都非常奇怪 是在库函数里报的错 作者的代码应该没有问题 想问一下作者当时运行的版本以及我在目录下面都要创建些什么呢 非常感谢!!!!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant