datamule 2.3.2__py3-none-any.whl → 2.3.4__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of datamule might be problematic. Click here for more details.
- datamule/datasets.py +5 -3
- datamule/document/document.py +2 -3
- datamule/mapping_dicts/html_mapping_dicts.py +1 -1
- {datamule-2.3.2.dist-info → datamule-2.3.4.dist-info}/METADATA +1 -1
- {datamule-2.3.2.dist-info → datamule-2.3.4.dist-info}/RECORD +7 -7
- {datamule-2.3.2.dist-info → datamule-2.3.4.dist-info}/WHEEL +0 -0
- {datamule-2.3.2.dist-info → datamule-2.3.4.dist-info}/top_level.txt +0 -0
datamule/datasets.py
CHANGED
|
@@ -8,7 +8,8 @@ import csv
|
|
|
8
8
|
# Dataset URLs
|
|
9
9
|
DATASET_URLS = {
|
|
10
10
|
"cik_cusip_crosswalk": "https://github.com/john-friedman/datamule-data/raw/refs/heads/master/data/datasets/cik_cusip_crosswalk.csv.gz",
|
|
11
|
-
"financial_security_identifiers_crosswalk" : "https://github.com/john-friedman/datamule-data/raw/refs/heads/master/data/datasets/financial_security_identifiers_crosswalk.csv.gz"
|
|
11
|
+
"financial_security_identifiers_crosswalk" : "https://github.com/john-friedman/datamule-data/raw/refs/heads/master/data/datasets/financial_security_identifiers_crosswalk.csv.gz",
|
|
12
|
+
"proposal_results" : "https://github.com/Structured-Output/SEC/raw/refs/heads/main/datasets/proposal_results.csv.gz"
|
|
12
13
|
}
|
|
13
14
|
|
|
14
15
|
def update_dataset(name):
|
|
@@ -43,9 +44,10 @@ def _get_dataset(name, update=False):
|
|
|
43
44
|
gz_path.unlink()
|
|
44
45
|
|
|
45
46
|
# Read CSV and return as list of dicts
|
|
46
|
-
with open(file_path, 'r') as f:
|
|
47
|
+
with open(file_path, 'r',encoding='utf-8') as f:
|
|
47
48
|
return list(csv.DictReader(f))
|
|
48
49
|
|
|
49
50
|
# Dataset available as list of dicts on import
|
|
50
51
|
cik_cusip_crosswalk = _get_dataset("cik_cusip_crosswalk")
|
|
51
|
-
financial_security_identifiers_crosswalk = _get_dataset("financial_security_identifiers_crosswalk")
|
|
52
|
+
financial_security_identifiers_crosswalk = _get_dataset("financial_security_identifiers_crosswalk")
|
|
53
|
+
proposal_results = _get_dataset('proposal_results')
|
datamule/document/document.py
CHANGED
|
@@ -1,10 +1,9 @@
|
|
|
1
1
|
import json
|
|
2
2
|
import csv
|
|
3
3
|
import re
|
|
4
|
-
from doc2dict import xml2dict, txt2dict
|
|
5
|
-
from doc2dict.mapping import flatten_hierarchy
|
|
4
|
+
from doc2dict import xml2dict, txt2dict
|
|
6
5
|
from doc2dict import html2dict, visualize_dict, get_title, unnest_dict, pdf2dict, flatten_dict
|
|
7
|
-
from ..mapping_dicts.txt_mapping_dicts import
|
|
6
|
+
from ..mapping_dicts.txt_mapping_dicts import dict_13d, dict_13g
|
|
8
7
|
from ..mapping_dicts.xml_mapping_dicts import dict_345
|
|
9
8
|
from ..mapping_dicts.html_mapping_dicts import *
|
|
10
9
|
from pathlib import Path
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
datamule/__init__.py,sha256=gsWTW0emwGtM-KVtwe2OICVmW7ImvLvP0SORULTPe-Y,1220
|
|
2
2
|
datamule/config.py,sha256=Y--CVv7JcgrjJkMOSLrvm2S8B9ost6RMSkGviP-MKtg,883
|
|
3
|
-
datamule/datasets.py,sha256
|
|
3
|
+
datamule/datasets.py,sha256=1A9PPPyLIQ51evXLSsiKmVxNmjbO6c2FGszrairREjc,2058
|
|
4
4
|
datamule/helper.py,sha256=KqhAmTMdvATEh3I-O4xLcAcrHB9zXQERBuwzue7zyQw,3674
|
|
5
5
|
datamule/index.py,sha256=Rrcna9FJV-Oh_K6O2IuUEIDmtay_7UZ4l4jgKCi7A7I,2079
|
|
6
6
|
datamule/package_updater.py,sha256=Z9zaa_y0Z5cknpRn8oPea3gg4kquFHfpfhduKKCZ6NU,958
|
|
@@ -18,7 +18,7 @@ datamule/datamule/datamule_mysql_rds.py,sha256=Q6_h24-SNECWK60RnM6UQjUIp5dhJmfn3
|
|
|
18
18
|
datamule/datamule/downloader.py,sha256=Ss9mz0Jf5UAd-CZJ6oO96o9hN04xMQIF3-e1wahokdM,18581
|
|
19
19
|
datamule/datamule/sec_connector.py,sha256=VwOaODpHoAWy8JIky6kLR1-orW_PB61RHw7pIGRpkow,3288
|
|
20
20
|
datamule/document/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
21
|
-
datamule/document/document.py,sha256=
|
|
21
|
+
datamule/document/document.py,sha256=ooTbMpB_cBeONhtic8bNE4ISWltQIxQz4LLuXcGe8xc,23015
|
|
22
22
|
datamule/document/tables/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
23
23
|
datamule/document/tables/tables.py,sha256=uEMDYg7c4iHjVtIjNQgCgZOGp6j9aFWVB05agpVsNOI,5727
|
|
24
24
|
datamule/document/tables/tables_13fhr.py,sha256=-6tWcaTyNsb0XuW0WMBrYir9Zn1wLZL0laKxRYfPNyg,4265
|
|
@@ -31,7 +31,7 @@ datamule/document/tables/tables_sbsef.py,sha256=X6VKVnAdWxn2TgRmaAd1WWlxPhcLPQ-5
|
|
|
31
31
|
datamule/document/tables/tables_sdr.py,sha256=BwHRJvtijiYvNJ2lIc_30kct6VEmLimIzX28JjZBBqo,4924
|
|
32
32
|
datamule/document/tables/utils.py,sha256=2-X_1NsiWj_XsD9djxCXwTeIVlg-ip78gG11xACJiDs,738
|
|
33
33
|
datamule/mapping_dicts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
34
|
-
datamule/mapping_dicts/html_mapping_dicts.py,sha256=
|
|
34
|
+
datamule/mapping_dicts/html_mapping_dicts.py,sha256=pba3utMr2KldPeEGnMRkHyVw7D2WHSDpg_5u36pHMII,5411
|
|
35
35
|
datamule/mapping_dicts/txt_mapping_dicts.py,sha256=DQPrGYbAPQxomRUtt4iiMGrwuF7BHc_LeFBQuYBzU9o,6311
|
|
36
36
|
datamule/mapping_dicts/xml_mapping_dicts.py,sha256=Z22yDVwKYonUfM5foQP00dVDE8EHhhMKp0CLqVKV5OI,438
|
|
37
37
|
datamule/sec/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
@@ -61,7 +61,7 @@ datamule/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
|
61
61
|
datamule/utils/construct_submissions_data.py,sha256=NB_hvfxlRXPyt4Fgc-5qA8vJRItkLhBedCSTaxwW7Jg,5887
|
|
62
62
|
datamule/utils/format_accession.py,sha256=60RtqoNqoT9zSKVb1DeOv1gncJxzPTFMNW4SNOVmC_g,476
|
|
63
63
|
datamule/utils/pdf.py,sha256=Z9xrdVhKex2YdvjYsaPaygRE_J6P_JNiUGkwflz2Hw0,735
|
|
64
|
-
datamule-2.3.
|
|
65
|
-
datamule-2.3.
|
|
66
|
-
datamule-2.3.
|
|
67
|
-
datamule-2.3.
|
|
64
|
+
datamule-2.3.4.dist-info/METADATA,sha256=TBPwdO8QYq6QDVKp6YHZTjV27vee5CHIkpX_tG4ROx4,609
|
|
65
|
+
datamule-2.3.4.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
|
|
66
|
+
datamule-2.3.4.dist-info/top_level.txt,sha256=iOfgmtSMFVyr7JGl_bYSTDry79JbmsG4p8zKq89ktKk,9
|
|
67
|
+
datamule-2.3.4.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|