Importing¶

[1]:

from CB_IPO import scrape

Initializing¶

[2]:

scraper = scrape()

Scraping for recent IPO filings (S-1)¶

[21]:

company_names, file_dates, form_types = scraper.edgar_scrape(5)
print(company_names)
print(file_dates[1:])
print(form_types)

['Intuitive Machines, Inc.  (LUNR, LUNRW) ', 'Nuburu, Inc.  (BURU, BURU-WT) ', 'SOLIGENIX, INC.  (SNGX) ', 'NovaBay Pharmaceuticals, Inc.  (NBY) ', 'Kodiak Gas Services, Inc. ']
['2023-03-31', '2023-03-31', '2023-03-31', '2023-03-31']
{'S-1', 'S-1/A'}

Formatting into Dataframe¶

[15]:

df = scraper.generate_df(6,1)
df.iloc[1:]

[15]:

	names	filing date
1	Nuburu, Inc. (BURU, BURU-WT)	2023-03-31
2	SOLIGENIX, INC. (SNGX)	2023-03-31
3	NovaBay Pharmaceuticals, Inc. (NBY)	2023-03-31
4	Kodiak Gas Services, Inc.	2023-03-31
5	Artificial Intelligence Technology Solutions I...	2023-03-31

Modifying Search Dates¶

[14]:

scraper.set_search_date("2021-01-01", "2023-03-31")

company_names, file_dates, form_types = scraper.edgar_scrape(5)

df = scraper.generate_df(6,1)
df.iloc[1:]

[14]:

	names	filing date
1	Nuburu, Inc. (BURU, BURU-WT)	2023-03-31
2	SOLIGENIX, INC. (SNGX)	2023-03-31
3	NovaBay Pharmaceuticals, Inc. (NBY)	2023-03-31
4	Kodiak Gas Services, Inc.	2023-03-31
5	Artificial Intelligence Technology Solutions I...	2023-03-31

Modifying Form Types¶

[13]:

scraper.reset_url()
scraper.set_search_date("2021-12-30", "2022-01-01")
scraper.add_forms(['10-K', '10-Q'])

company_names, file_dates, form_types = scraper.edgar_scrape(5)
print (form_types)

df = scraper.generate_df(6,1)
df.iloc[1:]

{'10-Q', '10-Q/A', '10-K'}

[13]:

	names	filing date
1	GOLDEN GRAIN ENERGY	2021-12-30
2	Financial Gravity Companies, Inc. (FGCO)	2021-12-30
3	NEOGEN CORP (NEOG)	2021-12-30
4	EASTON PHARMACEUTICALS INC.	2021-12-30
5	Nestbuilder.com Corp. (NBLD)	2021-12-30

Generating Reference Codes and Accession Numbers¶

[4]:

#This is the cik that identifies Pfizer
cik = '0000078003'

#This will yield all references and the name of a company tied to a cik
references, name = scraper.get_refs(cik,3)

#This will yield all accession numbers tied to a cik
accession_numbers = scraper.get_anums(cik,3)

print(accession_numbers)
print(references)
print(name)

['000007800323000024', '000007800322000027', '000007800321000038']
['pfe-20221231.htm', 'pfe-20211231.htm', 'pfe-20201231.htm']
PFIZER INC  (PFE)

Finding xbrl Links for a Company¶

[5]:

links,c_name = scraper.create_links(cik, 3)

for link in links:
    print(link)

https://www.sec.gov/ix?doc=/Archives/edgar/data/0000078003/000007800323000024/pfe-20221231.htm
https://www.sec.gov/ix?doc=/Archives/edgar/data/0000078003/000007800322000027/pfe-20211231.htm
https://www.sec.gov/ix?doc=/Archives/edgar/data/0000078003/000007800321000038/pfe-20201231.htm

Scraping Link for Financial Info and Calculating Ratio¶

[10]:

link = links[0]

Financials = scraper.scrape_xbrl(link)
for f in Financials.items():
    print(''+f[0]+': '+str(f[1]))
print()

ratios = scraper.calculate_ratios(Financials)

for f in ratios.items():
    print(''+f[0]+': '+str(f[1]))
print()

Total Assets: 197205.0
Total Liabilities: 101288.0
Total Equity: 95916.0
Current Assets: 51259.0
Current Liabilities: 42138
Net Income: 31372.0
Long Term Debt: 32884.0
Current Debt: 2945.0
Inventory: 8981.0
Registrant: PFIZER INC

D/E: 1.0560073397556196
ROE: 0.3270778597939864
Working Capital: 1.216455455883051
Quick: 1.0033224168209218
TD/TA: 0.181684034380467
ROA: 0.1590831875459547

10-K Dataframe Summary¶

[16]:

raw_df = scraper.summarize_10k(link, flag = 'raw')
ratio_df = scraper.summarize_10k(link, flag = 'liquidity')
lev_df = scraper.summarize_10k(link, flag = 'leverage')

display(raw_df)
print()
display(ratio_df)
print()
display(lev_df)

	Account	Amount
0	Total Assets	197205.0
1	Total Liabilities	101288.0
2	Total Equity	95916.0
3	Current Assets	51259.0
4	Current Liabilities	42138
5	Net Income	31372.0
6	Long Term Debt	32884.0
7	Current Debt	2945.0
8	Inventory	8981.0
9	Registrant	PFIZER INC

	Ratio	Value
0	Quick	1.003322
1	Working Capital	1.216455

	Ratio	Value
0	D/E	1.056007
1	TD/TA	0.181684