search

huaying / instagram-crawler

Get Instagram posts/profile/hashtag data without using Instagram API
MIT License
1.17k stars 288 forks source link

error when run python crawler.py posts #127

Open 8thstar opened 2 years ago

8thstar commented 2 years ago

Error occurred during loading data. Trying to use cache server https://fake-useragent.herokuapp.com/browsers/0.1.11 Traceback (most recent call last): File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\site-packages\fake_useragent\utils.py", line 154, in load for item in get_browsers(verify_ssl=verify_ssl): File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\site-packages\fake_useragent\utils.py", line 99, in get_browsers html = html.split('

')[1] IndexError: list index out of range Traceback (most recent call last): File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\site-packages\fake_useragent\utils.py", line 154, in load for item in get_browsers(verify_ssl=verify_ssl): File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\site-packages\fake_useragent\utils.py", line 99, in get_browsers html = html.split('
')[1] IndexError: list index out of range

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 1346, in do_open h.request(req.get_method(), req.selector, req.data, headers, File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\http\client.py", line 1285, in request self._send_request(method, url, body, headers, encode_chunked) File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\http\client.py", line 1331, in _send_request self.endheaders(body, encode_chunked=encode_chunked) File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\http\client.py", line 1280, in endheaders self._send_output(message_body, encode_chunked=encode_chunked) File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\http\client.py", line 1040, in _send_output self.send(msg) File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\http\client.py", line 980, in send self.connect() File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\http\client.py", line 1447, in connect super().connect() File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\http\client.py", line 946, in connect self.sock = self._create_connection( File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\socket.py", line 844, in create_connection raise err File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\socket.py", line 832, in create_connection sock.connect(sa) socket.timeout: timed out

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\site-packages\fake_useragent\utils.py", line 64, in get with contextlib.closing(urlopen( File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 214, in urlopen return opener.open(url, data, timeout) File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 517, in open response = self._open(req, data) File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 534, in _open result = self._call_chain(self.handle_open, protocol, protocol + File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 494, in _call_chain result = func(*args) File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 1389, in https_open return self.do_open(http.client.HTTPSConnection, req, File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 1349, in do_open raise URLError(err) urllib.error.URLError:

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "E:\insta crawler\crawler.py", line 82, in get_posts_by_user( File "E:\insta crawler\crawler.py", line 27, in get_posts_by_user ins_crawler = InsCrawler(has_screen=debug) File "E:\insta crawler\inscrawler\crawler.py", line 68, in init self.browser = Browser(has_screen) File "E:\insta crawler\inscrawler\browser.py", line 25, in init chrome_options.add_argument("user-agent="+UserAgent().random) File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\site-packages\fake_useragent\fake.py", line 69, in init self.load() File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\site-packages\fake_useragent\fake.py", line 75, in load self.data = load_cached( File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\site-packages\fake_useragent\utils.py", line 250, in load_cached update(path, use_cache_server=use_cache_server, verify_ssl=verify_ssl) File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\site-packages\fake_useragent\utils.py", line 245, in update write(path, load(use_cache_server=use_cache_server, verify_ssl=verify_ssl)) File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\site-packages\fake_useragent\utils.py", line 187, in load ret = json.loads(get( File "C:\Users\8thstar\AppData\Local\Programs\Python\Python39\lib\site-packages\fake_useragent\utils.py", line 84, in get raise FakeUserAgentError('Maximum amount of retries reached') fake_useragent.errors.FakeUserAgentError: Maximum amount of retries reached

jin749 commented 1 year ago

You can do this: pip install --upgrade fake-useragent

  • © Githubissues.
  • Githubissues is a development platform for aggregating issues.