forked from areed1192/python-sec
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathparser.py
More file actions
549 lines (403 loc) · 18.2 KB
/
Copy pathparser.py
File metadata and controls
549 lines (403 loc) · 18.2 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
import re
import xml.etree.ElementTree as ET
import requests
from pprint import pprint
from typing import List
from typing import Dict
from typing import Union
from html.parser import HTMLParser
from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry
from bs4 import BeautifulSoup
from bs4 import Tag
from bs4 import NavigableString
class EDGARParser():
def __init__(self):
"""Initalizes the `EDGARParser()` Object.
Parsing filings, can change depending on the filing you're working with
and whether you're grabbing the raw filing text or the directory of the filings.
Regardless of what you're parsing, the `EDGARParser()` object will handle most of
the finer details for you.
In cases, where the user needs to parse RSS feeds for the company search, then the
parser will grab all the XML content and convert it to a Python dictionary. Additionally,
it will grab all the next pages and parse thoses if specified.
"""
self.entries_namespace = {
'atom': "http://www.w3.org/2005/Atom",
'atom_with_quote':'{http://www.w3.org/2005/Atom}',
'':''
}
self.retry_strategy = Retry(
total=3,
backoff_factor=0.2,
status_forcelist=[429, 500, 502, 503, 504]
)
self.adapter = HTTPAdapter(max_retries=self.retry_strategy)
def parse_entries(self, entries_text: str, num_of_items: int = None, start: int = None) -> List[Dict]:
"""Parses all the entries from an entry element list.
Arguments:
----
entries_text {str} -- The raw string returned from the
response.
Returns:
----
List[Dict] -- A dictionary containing all the information from the
original entry element.
"""
# Parse the text.
root = ET.fromstring(entries_text)
entries = []
keep_going = True
if start:
current_count = start
else:
current_count = 0
while keep_going:
# Check for the next page Link, if there is one.
next_page = self._check_for_next_page(root_document=root)
# Grab the next page.
if next_page and start:
current_count = (int(next_page.split('&start=')[1]) - start)
elif next_page:
current_count = int(next_page.split('&start=')[1])
# Find all the entries.
for entry in root.findall('atom:entry', namespaces=self.entries_namespace):
# Parse the individual entry.
entry_dict = self.parse_entry_element(entry=entry)
entries.append(entry_dict)
# If there is a next page continue.
if not next_page:
keep_going = False
else:
root = self._grab_next_page(next_url=next_page)
print('Grabbed Next URL: {url}'.format(url=next_page))
if not root or (num_of_items and num_of_items < current_count):
keep_going = False
return entries
def _grab_next_page(self, next_url: str) -> ET.ElementTree:
"""Grabs the next page text content.
Grabbing mutliple pages can be challenging because in some
cases the SEC will kick you back if you make too many requests
at once and don't pause enough. This method will help control that
by defining a retry strategy and backing off for an allotted time
in the case of a failed request.
Arguments:
----
next_url {str} -- URL redirecting to the next rounds of files.
Returns:
----
ET.ElementTree -- A parsed version of the RSS Feed.
"""
# Create a new session.
http = requests.Session()
# Set the retry strategy.
http.mount("https://", self.adapter)
# Make the request.
try:
entries_response = http.get(url=next_url)
except:
return None
# If it was successful, get the data.
if entries_response.status_code == 200:
root = ET.fromstring(entries_response.content)
return root
else:
return None
def parse_entry_element(self, entry: ET.ElementTree) -> dict:
"""Converts the XML entry element into a python dictionary.
Arguments:
----
entry {ET.ElementTree} -- An entry element, that contains filing information.
Returns:
----
dict -- A dictionary version of the entry element.
"""
entry_element_dict = {}
replace_tag = self.entries_namespace['atom_with_quote']
for entry in entry.findall("./", namespaces=self.entries_namespace):
for element in entry.iter():
name = element.tag.replace(replace_tag, '')
if element.text :
name = name.replace('-','_')
entry_element_dict[name] = element.text.strip()
if element.attrib:
for key, value in element.attrib.items():
key = key.replace('-','_')
entry_element_dict[name + "_{}".format(key)] = value
return entry_element_dict
def _check_for_next_page(self, root_document: ET.Element) -> Union[str, None]:
"""Checks if the RSS Feed has a next page.
Arguments:
----
root_document {ET.Element} -- The Parsed root document, which contains entry
elements.
Returns:
----
Union[str, None] -- The URL if it was found otherwise nothing.
"""
next_page = root_document.findall("atom:link[@rel='next']", namespaces=self.entries_namespace)
if next_page:
element_attributes = next_page[0].attrib
else:
return None
if 'href' in element_attributes:
next_page_url = element_attributes['href']
else:
return None
return next_page_url
def _parse_issuer_next_button(self, button_soup: Tag) -> Union[str]:
"""Parses the next button in the issuer report.
Args:
----
button_soup (Tag): The raw HTML of the page with the button included.
Returns:
----
Union[str]: The link to the next page or nothing.
"""
# Grab the button.
buttons: Tag = button_soup.find_all(
name='input',
attrs={'type': 'button'}
)
# Loop through each of the buttons.
for button in buttons:
# If there is a next button, grab the link.
if 'Next' in button['value']:
next_page = button['onclick']
# Build the URL
next_page_link = next_page.replace("parent.location='","https://www.sec.gov").replace("'","")
return next_page_link
def parse_issuer_table(self, entries_text: str, num_of_items: int = None) -> List[Dict]:
"""Parses the Issuer tables found from a query to owner distribtuion page.
Arguments:
----
entries_text (str): The raw HTML content to be parsed.
num_of_items (int, optional): The number of items to return from the query. Defaults to None.
Returns:
----
List[Dict]: A list of dictionaries where each dictionary contains the `ownership_report`
and the `ownership_transaction_report`.
"""
master_list = []
ownership_report_for_issuers = []
soup = BeautifulSoup(entries_text, 'html.parser')
next_page_link = self._parse_issuer_next_button(button_soup=soup)
while soup is not None:
# table_rows = soup.find_all(name='tr')
table = soup.find_all(name='table')
issuers_table: Tag = table[4]
issuers_transaction_report_table: Tag = soup.find_all(
name='table',
attrs={
'id':'transaction-report'
}
)
issuers_table_rows = issuers_table.find_all(name='tr')
for row in issuers_table_rows:
issuer_dict = {}
row: Tag = row
elements = row.text.split('\n')
links = row.find_all('a', href=True)
issuer_dict = {
'issuer': elements[0],
'filings': elements[1],
'transaction_date': elements[2],
'type_of_owner': elements[3]
}
ownership_report_for_issuers.append(issuer_dict)
for link in links:
new_link = 'https://www.sec.gov' + link['href']
if 'own-disp' in new_link:
issuer_dict['ownership_link'] = new_link
elif 'browse-edgar' in new_link:
issuer_dict['browse_company_link'] = new_link
master_dict = {}
master_dict['ownership_report'] = ownership_report_for_issuers
master_dict['ownership_transaction_report'] = self.parse_transaction_report(
table=issuers_transaction_report_table[0]
)
master_list.append(master_dict)
print("Pulling URL: {url}".format(url=next_page_link))
if next_page_link:
entries_text = requests.get(next_page_link).content
soup = BeautifulSoup(entries_text, 'html.parser')
next_page_link = self._parse_issuer_next_button(button_soup=soup)
else:
soup = None
return master_list
def parse_transaction_report(self, table: Tag) -> List[Dict]:
"""Parse the transaction table report.
Arguments:
----
table (Tag): The raw HTML table.
Returns:
----
List[Dict]: A list of ownership transaction reports.
"""
master_list = []
all_rows = table.find_all('tr')
first_row = all_rows[0]
all_other_rows = all_rows[1:]
headers = [header.replace(' ', '_').lower() for header in first_row.strings if header != '\n']
headers.insert(5, 'link')
for row in all_other_rows:
link = row.find_all('a')[0]
href = 'https://www.sec.gov' + link['href']
values = [value.strip() for value in row.strings if value != '\n']
values.insert(5, href)
master_list.append(dict(zip(headers, values)))
# print([header.strip() for header in row.strings if header != '\n'])
return master_list
def _check_center_tag(self, product_table_soup: Tag) -> Union[List[str]]:
"""Grabs all the links that are in the Center tag of the Product Page.
Arguments:
----
product_table_soup (Tag): The product page HTML that has been parsed.
Returns:
----
Union[List[str]]: A list of URL links to the other pages.
"""
links = []
# Find the <center> tag.
center_tag: Tag = product_table_soup.find(name='center')
# Grab the <A> tags.
center_tag_hrefs = center_tag.find_all('a', href=True)
# We need to clean up the links, cause they're broken.
for href in center_tag_hrefs:
# Split by the ampersand.
split_href: list = href['href'].split('&')
# Remove the CIK parameters.
split_href.pop(1)
# and add a clean one.
split_href.insert(1, 'CIK=')
# Create a new URL.
links.append('https://www.sec.gov' + '&'.join(split_href))
# Don't care about the last one, just a duplicate.
return links[:-1]
def parse_variable_products_company_table(self, product_table_page: str) -> List[Dict]:
"""Parses the Variable Product page of all the different products and companies.
Arguments:
----
product_table_page (str): The raw HTML of the Product query result page.
Returns:
----
List[Dict]: A list of variable products.
"""
# Parse the Page.
product_page_soup = BeautifulSoup(product_table_page, 'html.parser')
# Check for the other links.
href_links = self._check_center_tag(product_table_soup=product_page_soup)
# Parse the table.
product_list_all = self._parse_variable_product_page(product_page_soup=product_page_soup)
# Loop through all the pages, and grab those entries.
for link in href_links:
product_page_soup = BeautifulSoup(requests.get(url=link).text, 'html.parser')
product_list = self._parse_variable_product_page(product_page_soup=product_page_soup)
product_list_all = product_list_all + product_list
print("Pulling URL: {url}".format(url=link))
print("Total Entries Scraped: {quant}".format(quant=len(product_list_all)))
return product_list_all
def _parse_variable_product_page(self, product_page_soup: Tag) -> List[Dict]:
"""This parses the actual table. It will grab the table with the entires and parse each row.
Arguments:
----
product_page_soup (Tag): The parsed page with product tables.
Returns:
----
List[Dict]: A list of variable products.
"""
# Grab all the Summary Tables.
summary_table = product_page_soup.find_all(name='table', attrs={'summary':'.'})
master_list = []
# Loop through each table.
for table in summary_table:
table: Tag = table
# Define a matching table.
criteria_1 = len(table.attrs) == 1
criteria_2 = table.attrs['summary'] == '.'
criteria_3 = len(table.find_all('input')) == 0
if criteria_1 and criteria_2 and criteria_3:
# Grab all the Rows.
table_rows: List[Tag] = table.find_all('tr', attrs={'valign':'top'})
# Loop through each Row.
for row in table_rows:
# Grab Row links
row_links = [row_link['href'] for row_link in row.find_all('a', href=True)]
# Grab the Strings, with text and filter our line breaks.
values = [string for string in row.strings if string != '\n']
if values:
# Create the dictionary & store the values.
row_dict = {}
product_id: str = values[0]
product_name: str = values[1]
row_dict['id'] = product_id
row_dict['name'] = product_name
# Define the product ID based on the first Character.
if product_id.startswith('S'):
row_dict['id_type'] = 'Series'
elif product_id.startswith('C'):
row_dict['id_type'] = 'Contract'
else:
row_dict['id_type'] = 'CIK'
# Set the Ticker symbol.
try:
row_dict['ticker_symbol'] = values[2]
except:
row_dict['ticker_symbol'] = "null"
for link in row_links:
if '&scd' in link:
row_dict['series_link'] = 'https://www.sec.gov' + link
elif 'getcompany' in link and row_dict['id_type'] == 'Contract':
row_dict['contract_id_link'] = 'https://www.sec.gov' + link
elif 'getcompany' in link and row_dict['id_type'] == 'Series':
row_dict['series_id_link'] = 'https://www.sec.gov' + link
else:
row_dict['cik_id_link'] = 'https://www.sec.gov' + link
master_list.append(row_dict)
return master_list
def parse_current_event_table(self, current_event_page: str) -> List[Dict]:
"""Parses the Current Event page of all the forms.
Arguments:
----
current_event_page (str): The raw HTML of the current event query page.
Returns:
----
List[Dict]: A list of SEC filings.
"""
master_list = []
# Parse the Page.
current_event_soup = BeautifulSoup(current_event_page, 'html.parser')
# Grab the <Pre> tag.
current_event_pre: Tag = current_event_soup.find('pre')
# In this case, split along Line breaks.
all_rows = current_event_pre.text.splitlines()
# Define the headers
keys = ['date_filed', 'form', 'cik', 'company_name']
# Clean up the header to get the first row.
header_row = all_rows[0].replace('Date Filed Form CIK Code Company Name','')
new_string = " ".join(header_row.split()).split(' ', 3)
# add to the list.
master_list.append(dict(zip(keys, new_string)))
# Clean up the rest of the rows.
for row in all_rows[1:]:
new_string = " ".join(row.split()).split(' ', 3)
master_list.append(dict(zip(keys, new_string)))
return master_list
def parse_loc_elements(self, response_text: str) -> List[dict]:
"""Parses the `Loc` elements found in the Taxonomies XML content.
Arguments:
----
response_text (str): The raw XML of the Taxonomy query.
Returns:
----
List[Dict]: A list of taxonomy objects..
"""
# Parse the text.
root = ET.fromstring(response_text)
entries = []
# Grab all the location elements.
for location in root.findall('Loc'):
location_dict = {element.tag: element.text for element in location.iter()}
del location_dict['Loc']
entries.append(location_dict)
return entries