Scraping des fichiers de la SEC EDGAR avec Python
Bonjour j'essaie de scraper des fichiers de la SEC EDGAR pour obtenir des données financières sur des sociétés:
Ci dessous les lignes de codes et l'erreur que j'obtiens
Merci d'avance pour votre aide
#Import libraries
import edgar
import pandas as pd
import requests
import html5lib
import lxml
#access to the SEC dierctory of quarterly reports since 2018
edgar.download_index("C:/Users/XXXX/Desktop/SEC_Files", 2018, "XXXXXX@orange.fr", skip_all_present_except_last=False)
#we look at APPLE through quaterly reports
Selectedcompany='Apple Inc.'
Selectedreport='10-Q'
#to get information to build the right URL to read with read_html
csv=pd.read_csv('C:/Users/Laurent/Desktop/SEC_Files/2022-QTR3.tsv',sep='\t',lineterminator='\r',names=None)
csv.columns.values[0]='Item'
companyreport=csv[(csv['Item'].str.contains(Selectedcompany))&(csv['Item'].str.contains(Selectedreport))]
Filing=companyreport['Item'].str.split('|')
Filing=Filing.to_list()
#to select HTML file for Apple including financial reports
for item in Filing[0]:
if 'html' in item:
report=item
url='https://www.sec.gov/Archives/'+report
my_header = { "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.75 Safari/537.36", "X-Requested-With": "XMLHttpRequest" }
html_page_text = requests.get(url, headers=my_header)
#create the URL
dfTables = pd.read_html(html_page_text.text);
document_index=dfTables[0].dropna()
document_name=document_index[document_index['Description'].str.contains(Selectedreport)]
document_name=document_name['Document'].str.split(' ')
document_name=document_name[0][0]
report=report.replace('-','').replace('index.html','')
url='https://www.sec.gov/Archives/'+report+'/'+document_name
url
#this is here where I collect an error => HTTPError: HTTP Error 403: Forbidden
df = pd.read_html(url)
for item in df:
BS=(item[0].str.contains('Total current liabilities') | item[0].str.contains('Total assets'))
if BS.any():
Balance_Sheet=item
Balanc_Sheet
HTTPError Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_7980\1123660223.py in <module>
5
6
----> 7 df = pd.read_html(url)
8 for item in df:
9 BS=(item[0].str.contains('Total current liabilities') | item[0].str.contains('Total assets'))
~\anaconda3\lib\site-packages\pandas\util\_decorators.py in wrapper(*args, **kwargs)
309 stacklevel=stacklevel,
310 )
--> 311 return func(*args, **kwargs)
312
313 return wrapper
~\anaconda3\lib\site-packages\pandas\io\html.py in read_html(io, match, flavor, header, index_col, skiprows, attrs, parse_dates, thousands, encoding, decimal, converters, na_values, keep_default_na, displayed_only)
1111 io = stringify_path(io)
1112
-> 1113 return _parse(
1114 flavor=flavor,
1115 io=io,
~\anaconda3\lib\site-packages\pandas\io\html.py in _parse(flavor, io, match, attrs, encoding, displayed_only, **kwargs)
917
918 try:
--> 919 tables = p.parse_tables()
920 except ValueError as caught:
921 # if `io` is an io-like object, check if it's seekable
~\anaconda3\lib\site-packages\pandas\io\html.py in parse_tables(self)
237 list of parsed (header, body, footer) tuples from tables.
238 """
--> 239 tables = self._parse_tables(self._build_doc(), self.match, self.attrs)
240 return (self._parse_thead_tbody_tfoot(table) for table in tables)
241
~\anaconda3\lib\site-packages\pandas\io\html.py in _build_doc(self)
756 pass
757 else:
--> 758 raise e
759 else:
760 if not hasattr(r, "text_content"):
~\anaconda3\lib\site-packages\pandas\io\html.py in _build_doc(self)
737 try:
738 if is_url(self.io):
--> 739 with urlopen(self.io) as f:
740 r = parse(f, parser=parser)
741 else:
~\anaconda3\lib\site-packages\pandas\io\common.py in urlopen(*args, **kwargs)
234 import urllib.request
235
--> 236 return urllib.request.urlopen(*args, **kwargs)
237
238
~\anaconda3\lib\urllib\request.py in urlopen(url, data, timeout, cafile, capath, cadefault, context)
212 else:
213 opener = _opener
--> 214 return opener.open(url, data, timeout)
215
216 def install_opener(opener):
~\anaconda3\lib\urllib\request.py in open(self, fullurl, data, timeout)
521 for processor in self.process_response.get(protocol, []):
522 meth = getattr(processor, meth_name)
--> 523 response = meth(req, response)
524
525 return response
~\anaconda3\lib\urllib\request.py in http_response(self, request, response)
630 # request was successfully received, understood, and accepted.
631 if not (200 <= code < 300):
--> 632 response = self.parent.error(
633 'http', request, response, code, msg, hdrs)
634
~\anaconda3\lib\urllib\request.py in error(self, proto, *args)
559 if http_err:
560 args = (dict, 'default', 'http_error_default') + orig_args
--> 561 return self._call_chain(*args)
562
563 # XXX probably also want an abstract factory that knows when it makes
~\anaconda3\lib\urllib\request.py in _call_chain(self, chain, kind, meth_name, *args)
492 for handler in handlers:
493 func = getattr(handler, meth_name)
--> 494 result = func(*args)
495 if result is not None:
496 return result
~\anaconda3\lib\urllib\request.py in http_error_default(self, req, fp, code, msg, hdrs)
639 class HTTPDefaultErrorHandler(BaseHandler):
640 def http_error_default(self, req, fp, code, msg, hdrs):
--> 641 raise HTTPError(req.full_url, code, msg, hdrs, fp)
642
643 class HTTPRedirectHandler(BaseHandler):
HTTPError: HTTP Error 403: Forbidden
Répondre avec citation
Envoyé par ElGringo56
comme 
Partager