Is there a way to find specific values in a table and make it a df? - python-3.x

Question

I have an excel file which looks like this. I want to read it and take the dataframe1 with data1 in a df and dataframe2 with data2 in another df. The location of these data can be random. Is there a way to find it and make it a df?
the tables does not exist in the same position always but the headers are always consistent.
import pandas as pd
from openpyxl import load_workbook
wb = load_workbook('Book1.xlsx',data_only=True)
ws = wb.active
df = pd.DataFrame()
for row in ws.iter_rows():
for cell in row:
if cell.value == 'data1':
print('found')
df = pd.read_excel('test123.xlsx', sheet_name='Sheet1', skiprows=cell.row, nrows=2, usecols=range(cell.col-1,cell.col+3))
print(df)

Answer 1

Here is a class that should work. data_range arg should be a range much larger than where the data is located.
import re
import numpy as np
import pandas as pd
from openpyxl import load_workbook
from openpyxl.utils import get_column_interval
class ExcelDataFinder:
"""
param: data_range: str
param: search_for: list or str
return: list or pd.DataFrame
"""
def __init__(self, **kwargs):
path = "/Users/joeblow/Documents/test.xlsx"
self.work_book = load_workbook(filename=path, read_only=True, data_only=True)
self.data_range = kwargs.get("data_range")
self.search_for = kwargs.get("search_for")
def main(self) -> pd.DataFrame or list:
return self.find_data_from_list() if isinstance(self.search_for, list) else self.find_data_from_string()
def load_workbook_range(self) -> pd.DataFrame:
col_start, col_end = re.findall("[A-Z]+", self.data_range)
data_rows = [[x.value for x in row] for row in self.work_book.active[self.data_range]]
return pd.DataFrame(data_rows, columns=get_column_interval(col_start, col_end))
def find_data_from_string(self) -> pd.DataFrame:
df = self.load_workbook_range().fillna(np.nan)
df = df[np.where(df.eq(self.search_for))[0][0]:]
df = df.rename(columns=df.iloc[0]).drop(df.index[0]).reset_index(drop=True)
try:
return df.drop(columns=np.nan).dropna(how="all", axis=0).dropna(how="all", axis=1).reset_index(drop=True)
except KeyError:
pass
return df
def find_data_from_list(self) -> list:
dfs = []
for value in self.search_for:
df = self.load_workbook_range().fillna(np.nan)
df = df[np.where(df.eq(value))[0][0]:]
df = df.rename(columns=df.iloc[0]).drop(df.index[0]).reset_index(drop=True)
try:
df = df.drop(columns=np.nan).dropna(how="all", axis=0).dropna(how="all", axis=1).reset_index(drop=True)
except KeyError:
pass
dfs.append(df)
return dfs
if __name__ == "__main__":
df1, df2 = ExcelDataFinder(data_range="A1:Z5000", search_for=["dataframe1", "dataframe2"]).main()
print(f"{df1}\n")
print(df2)
dataframe1 data1
0 A610 656
1 B655 353
2 C698 876
dataframe2 data2
0 A611 654
1 B646 454
2 C694 796