junte/survey-extraction
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/survey-extraction.git synced 2026-06-08 11:17:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

made into a function for two column things

Browse source
This commit is contained in:
Jun-te Kim 2025-03-12 12:54:48 +00:00
parent 2d10ea2f80
commit 7aa694a5ff
2 changed files with 33 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
etl/main.py
View file

@ -10,9 +10,9 @@ DATA_LOC_1 = "/tmp/sharepoint/Abdul Koddus/W.C. 03.03.2025/Southern Housing/10 T
DATA_LOC_2 = "/tmp/sharepoint/Abdul Koddus/W.C. 03.03.2025/Southern Housing/16 Sunningdale Drive TN38 0WB/PRE SITE NOTES.pdf"
pdfReader = pdfReaderToText(DATA_LOC_1)
doc1 = pdfReader.get_reader()
doc2 = pdfReader.get_reader()
pdfReader2 = pdfReaderToText(DATA_LOC_2)
doc2 = pdfReader2.get_reader()
doc1 = pdfReader2.get_reader()
def main():

35
etl/pdfReader/sitenotes.py
View file

@ -31,6 +31,7 @@ class QuidosSiteNotes(SiteNotes):
self.get_section_6()
self.get_section_7()
self.get_section_8()
self.get_section_9()
def get_summary_information(self):
# Summary Information
@ -283,22 +284,48 @@ class QuidosSiteNotes(SiteNotes):
"Extension 3",
"Extension 4",
]
title = titles[0].lower().replace(" ", "_").replace("-","_")
self.two_column_with_extension_processor(data, avoid, titles, 8)
def two_column_with_extension_processor(self, data, avoid, titles, section):
title = None
proc_data = data
for items in data:
if items in titles:
title = items.lower().replace(" ", "_").replace("-", "_")
index = titles.index(items)
if titles[index] in data:
print(titles[index])
proc_data = data[data.index(titles[index]):]
continue
else:
break
if title is None:
continue
get_value = lambda key: None if proc_data[proc_data.index(key) + 1] in avoid else proc_data[proc_data.index(key) + 1]
if items in avoid:
setattr(self, f"section_8_{title}_{items.lower().replace(' ', '_').replace('-','_')}", get_value(items))
setattr(self, f"section_{section}_{title}_{items.lower().replace(' ', '_').replace('-','_')}", get_value(items))
def get_section_9(self):
data = self.raw_data[self.raw_data.index('9.0 Floors'): self.raw_data.index('10.0 Doors')]
avoid = [
"Floor Type",
"Ground Floor Construction",
"Ground Floor Insulation Type",
"Floor Insulation Thickness (mm)",
"U-value Known",
]
titles = [
"Main Property",
"Extension 1",
"Extension 2",
"Extension 3",
"Extension 4",
]
self.two_column_with_extension_processor(data, avoid, titles, 9)