def function10(): alldatadf = pd.DataFrame() for domain, df in zip(basedomains, dflist):…
- User
def function10(): all_data_df = pd.DataFrame()
for domain, df in zip(base_domains, df_list): # List of URLs to scrape urls = [f"https://{domain}/{slug}" for slug in df["URL"][:-1]] for idx, url in enumerate(urls): all_data = [] driver.get(url) div_content_driver = driver.find_element(By.ID, "prepared_content") select_element = div_content_driver.find_element(By.XPATH, ".//select") select = Select(select_element) while select.first_selected_option.get_attribute('value') != "-1": select.select_by_value("-1") html_content = driver.page_source soup = BeautifulSoup(html_content, "html.parser") div_content = soup.find("div", {"id": "prepared_content"}) table = div_content.find("table", {"class": "opt_task_table"}) if div_content else None # find table in each page if table: data = [] prev_row = None first_row = True budget_div = soup.find("div", class_="head") if budget_div: h5_element = budget_div.find("h5") if h5_element: klient_name = h5_element.text.split(" - Budżet")[0].strip() else: klient_name = "Unknown Client" else: klient_name = "Unknown Client" for tr in table.find_all("tr"): if first_row: first_row = False continue tds = tr.find_all("td") if len(tds) >= 6: row_data = [tds[i].get_text().strip() for i in [1, 2, 4, 5]] row_data_without_type = [row_data[0], row_data[-2], row_data[-1]] if all(row_data): if prev_row is None or row_data_without_type != prev_row_data_without_type: all_data.append(row_data) prev_row = row_data prev_row_data_without_type = row_data_without_type else: print(f"Same row as previous, not appended: {row_data}") else: print(f"Row skipped due to missing columns: {[td.get_text().strip() for td in tds]}") all_data.extend(data) all_data_with_klient = [[klient_name] + row for row in all_data] df_data = pd.DataFrame(all_data_with_klient, columns=["Klient", "Zadanie tekstowe", "Data dodania", "Status", "Wykonawca"]) all_data_df = pd.concat([all_data_df, df_data], ignore_index=True) # Filter the DataFrame to separate rows with status "nowe". filtered_df_nowe = all_data_df[all_data_df['Status'] == 'nowe'] # Format emails before grouping filtered_df_nowe['Wykonawca'] = filtered_df_nowe['Wykonawca'].apply(format_email) # Group the DataFrame by 'Wykonawca' (email address) grouped_df = filtered_df_nowe.groupby('Wykonawca') # Save the filtered DataFrame to a separate CSV file. # if you want use groupby usage is: .groupby(['Wykonawca', 'Klient']).sum().reset_index() or to_csv dosent work filtered_df_nowe.groupby(['Wykonawca', 'Klient']).sum().reset_index().to_csv("filtered_nowe_data.csv", index=False) print("Filtered 'nowe' data saved to filtered_nowe_data.csv") # Now, filter out rows with None 'Wykonawca' before creating messages filtered_df_nowe = filtered_df_nowe.dropna(subset=['Wykonawca'])i want add couting rows in this function, i want to df_data Data frame add next column which will count how much rows are merged with skipped ones so i can know how much texts were published i also want to add this count number in filtered_df_nowe
- Assistant
Certainly! You can achieve this by maintaining a separate counter that counts how many texts have been skipped (not appended). Then you can add that count as a new column to the
df_dataDataFrame and then propagate it tofiltered_df_nowe.Here's the modified version of your function with the added counting logic incorporated:
import pandas as pd from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.support.select import Select from bs4 import BeautifulSoup def format_email(email): # Assuming format_email function is defined elsewhere return email.strip().lower() def function10(): all_data_df = pd.DataFrame() for domain, df in zip(base_domains, df_list): # List of URLs to scrape urls = [f"https://{domain}/{slug}" for slug in df["URL"][:-1]] for idx, url in enumerate(urls): all_data = [] driver.get(url) div_content_driver = driver.find_element(By.ID, "prepared_content") select_element = div_content_driver.find_element(By.XPATH, ".//select") select = Select(select_element) while select.first_selected_option.get_attribute('value') != "-1": select.select_by_value("-1") html_content = driver.page_source soup = BeautifulSoup(html_content, "html.parser") div_content = soup.find("div", {"id": "prepared_content"}) table = div_content.find("table", {"class": "opt_task_table"}) if div_content else None # find table in each page if table: data = [] prev_row = None prev_row_data_without_type = None first_row = True skipped_count = 0 budget_div = soup.find("div", class_="head") if budget_div: h5_element = budget_div.find("h5") if h5_element: klient_name = h5_element.text.split(" - Budżet")[0].strip() else: klient_name = "Unknown Client" else: klient_name = "Unknown Client" for tr in table.find_all("tr"): if first_row: first_row = False continue tds = tr.find_all("td") if len(tds) >= 6: row_data = [tds[i].get_text().strip() for i in [1, 2, 4, 5]] row_data_without_type = [row_data[0], row_data[-2], row_data[-1]] if all(row_data): if prev_row is None or row_data_without_type != prev_row_data_without_type: all_data.append(row_data) prev_row = row_data prev_row_data_without_type = row_data_without_type else: print(f"Same row as previous, not appended: {row_data}") skipped_count += 1 else: print(f"Row skipped due to missing columns: {[td.get_text().strip() for td in tds]}") skipped_count += 1 all_data_with_klient_and_count = [[klient_name] + row + [skipped_count] for row in all_data] df_data = pd.DataFrame(all_data_with_klient_and_count, columns=["Klient", "Zadanie tekstowe", "Data dodania", "Status", "Wykonawca", "Skipped Count"]) all_data_df = pd.concat([all_data_df, df_data], ignore_index=True) # Filter the DataFrame to separate rows with status "nowe". filtered_df_nowe = all_data_df[all_data_df['Status'] == 'nowe'] # Format emails before grouping filtered_df_nowe['Wykonawca'] = filtered_df_nowe['Wykonawca'].apply(format_email) # Group the DataFrame by 'Wykonawca' (email address) grouped_df = filtered_df_nowe.groupby('Wykonawca') # Add a count column to filtered_df_nowe filtered_df_nowe['Count'] = filtered_df_nowe.groupby('Wykonawca')['Wykonawca'].transform('size') # Save the filtered DataFrame to a separate CSV file. filtered_df_nowe.groupby(['Wykonawca', 'Klient']).sum().reset_index().to_csv("filtered_nowe_data.csv", index=False) print("Filtered 'nowe' data saved to filtered_nowe_data.csv") # Now, remove rows with None 'Wykonawca' before creating messages filtered_df_nowe = filtered_df_nowe.dropna(subset=['Wykonawca']) # Make sure to define base_domains, df_list, driver, and initiate driver properly before calling this function.This code introduces a
skipped_countvariable that increments each time a row is skipped. This count is then added as a new columnSkipped Countin thedf_dataDataFrame. Additionally, aCountcolumn is added to thefiltered_df_noweDataFrame to indicate how many texts were published by eachWykonawca. - User
i mean i want count skipped, but with its original row, so i count how much are this same rows, so you need to count also first one and than skipped
- Assistant
I understand now. You want to count the total number of duplicated rows (including the first instance) and append this count to the DataFrame. Let's modify the function to keep track of these counts more accurately.
Here's the updated code with the requested feature:
import pandas as pd from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.support.ui import Select from bs4 import BeautifulSoup def format_email(email): # Assuming format_email function is defined elsewhere return email.strip().lower() def function10(): all_data_df = pd.DataFrame() for domain, df in zip(base_domains, df_list): # List of URLs to scrape urls = [f"https://{domain}/{slug}" for slug in df["URL"][:-1]] for idx, url in enumerate(urls): all_data = [] driver.get(url) div_content_driver = driver.find_element(By.ID, "prepared_content") select_element = div_content_driver.find_element(By.XPATH, ".//select") select = Select(select_element) while select.first_selected_option.get_attribute('value') != "-1": select.select_by_value("-1") html_content = driver.page_source soup = BeautifulSoup(html_content, "html.parser") div_content = soup.find("div", {"id": "prepared_content"}) table = div_content.find("table", {"class": "opt_task_table"}) if div_content else None # find table in each page if table: data = [] prev_row = None prev_row_data_without_type = None first_row = True budget_div = soup.find("div", class_="head") if budget_div: h5_element = budget_div.find("h5") if h5_element: klient_name = h5_element.text.split(" - Budżet")[0].strip() else: klient_name = "Unknown Client" else: klient_name = "Unknown Client" row_count = {} for tr in table.find_all("tr"): if first_row: first_row = False continue tds = tr.find_all("td") if len(tds) >= 6: row_data = [tds[i].get_text().strip() for i in [1, 2, 4, 5]] row_data_without_type = tuple([row_data[0], row_data[-2], row_data[-1]]) if all(row_data): if row_data_without_type not in row_count: row_count[row_data_without_type] = 1 all_data.append(row_data) else: row_count[row_data_without_type] += 1 all_data.append(row_data) else: print(f"Row skipped due to missing columns: {[td.get_text().strip() for td in tds]}") all_data_with_klient_and_count = [[klient_name] + row + [row_count[tuple([row[0], row[2], row[3]])]] for row in all_data] df_data = pd.DataFrame(all_data_with_klient_and_count, columns=["Klient", "Zadanie tekstowe", "Data dodania", "Status", "Wykonawca", "Duplicate Count"]) all_data_df = pd.concat([all_data_df, df_data], ignore_index=True) # Filter the DataFrame to separate rows with status "nowe". filtered_df_nowe = all_data_df[all_data_df['Status'] == 'nowe'] # Format emails before grouping filtered_df_nowe['Wykonawca'] = filtered_df_nowe['Wykonawca'].apply(format_email) # Group the DataFrame by 'Wykonawca' (email address) grouped_df = filtered_df_nowe.groupby('Wykonawca') # Add a count column to filtered_df_nowe filtered_df_nowe['Count'] = filtered_df_nowe.groupby('Wykonawca')['Wykonawca'].transform('size') # Save the filtered DataFrame to a separate CSV file. grouped = filtered_df_nowe.groupby(['Wykonawca', 'Klient']).sum().reset_index() grouped.to_csv("filtered_nowe_data.csv", index=False) print("Filtered 'nowe' data saved to filtered_nowe_data.csv") # Now, remove rows with None 'Wykonawca' before creating messages filtered_df_nowe = filtered_df_nowe.dropna(subset=['Wykonawca']) # Make sure to define base_domains, df_list, driver, and initiate driver properly before calling this function.Changes made:
- Introduced a dictionary
row_countto keep track of the number of times each row (excluding its type) appears. - Each time a unique row pattern is encountered, it initializes its count in the dictionary.
- When a duplicate is detected, it increases its count and appends it to the list.
- After processing the table, it creates
df_datawith an additional columnDuplicate Countshowing how many times each row was merged (including the first instance). - Finally, with the
filtered_df_nowe, it groups by 'Wykonawca' and 'Klient' to save the counted and filtered data into a CSV file.
- Introduced a dictionary
- User
No this is not what im looking for, i want to count all rows, but add count once at first element, i want to do the job as its now, and than add count, so for exmaple i have 5 same rows, first is added to a file, 4 are skipped i want just this one rows with count number in last column. What you provided dosent work as that so here is function which you should modify from begginging
def function10(): all_data_df = pd.DataFrame()
for domain, df in zip(base_domains, df_list): # List of URLs to scrape urls = [f"https://{domain}/{slug}" for slug in df["URL"][:-1]] for idx, url in enumerate(urls): all_data = [] driver.get(url) div_content_driver = driver.find_element(By.ID, "prepared_content") select_element = div_content_driver.find_element(By.XPATH, ".//select") select = Select(select_element) while select.first_selected_option.get_attribute('value') != "-1": select.select_by_value("-1") html_content = driver.page_source soup = BeautifulSoup(html_content, "html.parser") div_content = soup.find("div", {"id": "prepared_content"}) table = div_content.find("table", {"class": "opt_task_table"}) if div_content else None # find table in each page if table: data = [] prev_row = None first_row = True budget_div = soup.find("div", class_="head") if budget_div: h5_element = budget_div.find("h5") if h5_element: klient_name = h5_element.text.split(" - Budżet")[0].strip() else: klient_name = "Unknown Client" else: klient_name = "Unknown Client" for tr in table.find_all("tr"): if first_row: first_row = False continue tds = tr.find_all("td") if len(tds) >= 6: row_data = [tds[i].get_text().strip() for i in [1, 2, 4, 5]] row_data_without_type = [row_data[0], row_data[-2], row_data[-1]] if all(row_data): if prev_row is None or row_data_without_type != prev_row_data_without_type: all_data.append(row_data) prev_row = row_data prev_row_data_without_type = row_data_without_type else: print(f"Same row as previous, not appended: {row_data}") else: print(f"Row skipped due to missing columns: {[td.get_text().strip() for td in tds]}") all_data.extend(data) all_data_with_klient = [[klient_name] + row for row in all_data] df_data = pd.DataFrame(all_data_with_klient, columns=["Klient", "Zadanie tekstowe", "Data dodania", "Status", "Wykonawca"]) all_data_df = pd.concat([all_data_df, df_data], ignore_index=True) # Filter the DataFrame to separate rows with status "nowe". filtered_df_nowe = all_data_df[all_data_df['Status'] == 'nowe'] # Format emails before grouping filtered_df_nowe['Wykonawca'] = filtered_df_nowe['Wykonawca'].apply(format_email) # Group the DataFrame by 'Wykonawca' (email address) grouped_df = filtered_df_nowe.groupby('Wykonawca') # Save the filtered DataFrame to a separate CSV file. # if you want use groupby usage is: .groupby(['Wykonawca', 'Klient']).sum().reset_index() or to_csv dosent work filtered_df_nowe.groupby(['Wykonawca', 'Klient']).sum().reset_index().to_csv("filtered_nowe_data.csv", index=False) print("Filtered 'nowe' data saved to filtered_nowe_data.csv") # Now, filter out rows with None 'Wykonawca' before creating messages filtered_df_nowe = filtered_df_nowe.dropna(subset=['Wykonawca']) # Loop through each group and write messages to separate files for email, group in grouped_df: if email is not None: with open(f"messages_{email.replace('@', '_')}.txt", "w") as f: for index, row in group.iterrows(): # Split the date string into components day, month_name, year, time = row['Data dodania'].split() month = month_mapping[month_name] # Reconstruct the date string with numerical month date_str = f"{year}-{month:02d}-{day} {time}" # Parse the datetime string and format it to show only the date date_only = datetime.strptime(date_str, "%Y-%m-%d %H:%M").strftime("%d.%m.%Y") message = ( f"Klient {row['Klient']} został zlecony " f"{date_only} " f"i nie został jeszcze ukończony.\n" ) f.write(message) print(f"Messages for {email} written to messages_{email.replace('@', '_')}.txt") # Save the combined DataFrame to the main CSV file. all_data_df.to_csv("combined_scraped_data.csv", index=False) print("All data saved to combined_scraped_data.csv")Run the function10
function10()
- Assistant
Got it. If the goal is to count all rows (including the ones that were skipped) but only add the count to the instance of the row, we can keep track of the number of each unique row encountered in a dictionary. Then, after processing the table, we can append the count to the first occurrence of each unique row.
Here's how you can adjust your function to achieve this:
import pandas as pd from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.support.ui import Select from bs4 import BeautifulSoup from datetime import datetime # Assuming format_email and month_mapping are defined somewhere def format_email(email): return email.strip().lower() month_mapping = { "January": 1, "February": 2, "March": 3, "April": 4, "May": 5, "June": 6, "July": 7, "August": 8, "September": 9, "October": 10, "November": 11, "December": 12 } def function10(): all_data_df = pd.DataFrame() for domain, df in zip(base_domains, df_list): # List of URLs to scrape urls = [f"https://{domain}/{slug}" for slug in df["URL"][:-1]] for idx, url in enumerate(urls): all_data = [] row_counter = {} driver.get(url) div_content_driver = driver.find_element(By.ID, "prepared_content") select_element = div_content_driver.find_element(By.XPATH, ".//select") select = Select(select_element) while select.first_selected_option.get_attribute('value') != "-1": select.select_by_value("-1") html_content = driver.page_source soup = BeautifulSoup(html_content, "html.parser") div_content = soup.find("div", {"id": "prepared_content"}) table = div_content.find("table", {"class": "opt_task_table"}) if div_content else None # find table in each page if table: data = [] prev_row_data_without_type = None first_row = True budget_div = soup.find("div", class_="head") if budget_div: h5_element = budget_div.find("h5") if h5_element: klient_name = h5_element.text.split(" - Budżet")[0].strip() else: klient_name = "Unknown Client" else: klient_name = "Unknown Client" for tr in table.find_all("tr"): if first_row: first_row = False continue tds = tr.find_all("td") if len(tds) >= 6: row_data = [tds[i].get_text().strip() for i in [1, 2, 4, 5]] row_data_without_type = tuple([row_data[0], row_data[2], row_data[3]]) if all(row_data): if row_data_without_type not in row_counter: row_counter[row_data_without_type] = 0 row_counter[row_data_without_type] += 1 if prev_row_data_without_type != row_data_without_type: all_data.append(row_data) prev_row_data_without_type = row_data_without_type else: print(f"Same row as previous, not appended: {row_data}") else: print(f"Row skipped due to missing columns: {[td.get_text().strip() for td in tds]}") all_data_with_klient_and_count = [ [klient_name] + row + [row_counter[tuple([row[0], row[2], row[3]])]] for row in all_data ] df_data = pd.DataFrame(all_data_with_klient_and_count, columns=["Klient", "Zadanie tekstowe", "Data dodania", "Status", "Wykonawca", "Duplicate Count"]) all_data_df = pd.concat([all_data_df, df_data], ignore_index=True) # Filter the DataFrame to separate rows with status "nowe". filtered_df_nowe = all_data_df[all_data_df['Status'] == 'nowe'] # Format emails before grouping filtered_df_nowe['Wykonawca'] = filtered_df_nowe['Wykonawca'].apply(format_email) # Group the DataFrame by 'Wykonawca' (email address) grouped_df = filtered_df_nowe.groupby('Wykonawca') # Add a count column to filtered_df_nowe filtered_df_nowe['Count'] = filtered_df_nowe.groupby('Wykonawca')['Wykonawca'].transform('size') # Save the filtered DataFrame to a separate CSV file. filtered_df_nowe.groupby(['Wykonawca', 'Klient']).sum().reset_index().to_csv("filtered_nowe_data.csv", index=False) print("Filtered 'nowe' data saved to filtered_nowe_data.csv") # Now, filter out rows with None 'Wykonawca' before creating messages filtered_df_nowe = filtered_df_nowe.dropna(subset=['Wykonawca']) # Loop through each group and write messages to separate files for email, group in grouped_df: if email is not None: with open(f"messages_{email.replace('@', '_')}.txt", "w") as f: for index, row in group.iterrows(): # Split the date string into components day, month_name, year, time = row['Data dodania'].split() month = month_mapping[month_name] # Reconstruct the date string with numerical month date_str = f"{year}-{month:02d}-{day} {time}" # Parse the datetime string and format it to show only the date date_only = datetime.strptime(date_str, "%Y-%m-%d %H:%M").strftime("%d.%m.%Y") message = ( f"Klient {row['Klient']} został zlecony " f"{date_only} " f"i nie został jeszcze ukończony.\n" ) f.write(message) print(f"Messages for {email} written to messages_{email.replace('@', '_')}.txt") # Save the combined DataFrame to the main CSV file. all_data_df.to_csv("combined_scraped_data.csv", index=False) print("All data saved to combined_scraped_data.csv") # Run the function10 function10()Changes made:
- Kept a dictionary
row_counterto track the occurrence of each unique row data. - When processing each row, updated the
row_counterfor each unique row pattern. - Added a new column
Duplicate Countonly in the first occurrence of each unique row pattern. - Continued with the existing filtering and file writing logic as before.
This will ensure that only the first instance of each row has the count of how many times that row pattern appeared, with a column
Duplicate Countshowing the total count of that row pattern. - Kept a dictionary
- User
if all(row_data): if row_data_without_type not in row_counter: row_counter[row_data_without_type] = 0 row_counter[row_data_without_type] += 1
if prev_row_data_without_type != row_data_without_type: all_data.append(row_data) prev_row_data_without_type = row_data_without_type else: print(f"Same row as previous, not appended: {row_data}") else: print(f"Row skipped due to missing columns: {[td.get_text().strip() for td in tds]}")im getting here if prev_row_data_without_type != row_data_without_type: IndentationError: unexpected indent
- Assistant
I see the issue. The indentation error was caused by misaligned indentation in the conditional blocks. Here's the corrected function:
import pandas as pd from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.support.ui import Select from bs4 import BeautifulSoup from datetime import datetime # Assuming format_email and month_mapping are defined somewhere def format_email(email): return email.strip().lower() month_mapping = { "January": 1, "February": 2, "March": 3, "April": 4, "May": 5, "June": 6, "July": 7, "August": 8, "September": 9, "October": 10, "November": 11, "December": 12 } def function10(): all_data_df = pd.DataFrame() for domain, df in zip(base_domains, df_list): # List of URLs to scrape urls = [f"https://{domain}/{slug}" for slug in df["URL"][:-1]] for idx, url in enumerate(urls): all_data = [] row_counter = {} driver.get(url) div_content_driver = driver.find_element(By.ID, "prepared_content") select_element = div_content_driver.find_element(By.XPATH, ".//select") select = Select(select_element) while select.first_selected_option.get_attribute('value') != "-1": select.select_by_value("-1") html_content = driver.page_source soup = BeautifulSoup(html_content, "html.parser") div_content = soup.find("div", {"id": "prepared_content"}) table = div_content.find("table", {"class": "opt_task_table"}) if div_content else None # find table in each page if table: data = [] prev_row_data_without_type = None first_row = True budget_div = soup.find("div", class_="head") if budget_div: h5_element = budget_div.find("h5") if h5_element: klient_name = h5_element.text.split(" - Budżet")[0].strip() else: klient_name = "Unknown Client" else: klient_name = "Unknown Client" for tr in table.find_all("tr"): if first_row: first_row = False continue tds = tr.find_all("td") if len(tds) >= 6: row_data = [tds[i].get_text().strip() for i in [1, 2, 4, 5]] row_data_without_type = tuple([row_data[0], row_data[2], row_data[3]]) if all(row_data): if row_data_without_type not in row_counter: row_counter[row_data_without_type] = 0 row_counter[row_data_without_type] += 1 if prev_row_data_without_type != row_data_without_type: all_data.append(row_data) prev_row_data_without_type = row_data_without_type else: print(f"Same row as previous, not appended: {row_data}") else: print(f"Row skipped due to missing columns: {[td.get_text().strip() for td in tds]}") all_data_with_klient_and_count = [ [klient_name] + row + [row_counter[tuple([row[0], row[2], row[3]])]] for row in all_data ] df_data = pd.DataFrame(all_data_with_klient_and_count, columns=["Klient", "Zadanie tekstowe", "Data dodania", "Status", "Wykonawca", "Duplicate Count"]) all_data_df = pd.concat([all_data_df, df_data], ignore_index=True) # Filter the DataFrame to separate rows with status "nowe". filtered_df_nowe = all_data_df[all_data_df['Status'] == 'nowe'] # Format emails before grouping filtered_df_nowe['Wykonawca'] = filtered_df_nowe['Wykonawca'].apply(format_email) # Group the DataFrame by 'Wykonawca' (email address) grouped_df = filtered_df_nowe.groupby('Wykonawca') # Add a count column to filtered_df_nowe filtered_df_nowe['Count'] = filtered_df_nowe.groupby('Wykonawca')['Wykonawca'].transform('size') # Save the filtered DataFrame to a separate CSV file. filtered_df_nowe.groupby(['Wykonawca', 'Klient']).sum().reset_index().to_csv("filtered_nowe_data.csv", index=False) print("Filtered 'nowe' data saved to filtered_nowe_data.csv") # Now, filter out rows with None 'Wykonawca' before creating messages filtered_df_nowe = filtered_df_nowe.dropna(subset=['Wykonawca']) # Loop through each group and write messages to separate files for email, group in grouped_df: if email is not None: with open(f"messages_{email.replace('@', '_')}.txt", "w") as f: for index, row in group.iterrows(): # Split the date string into components day, month_name, year, time = row['Data dodania'].split() month = month_mapping[month_name] # Reconstruct the date string with numerical month date_str = f"{year}-{month:02d}-{day} {time}" # Parse the datetime string and format it to show only the date date_only = datetime.strptime(date_str, "%Y-%m-%d %H:%M").strftime("%d.%m.%Y") message = ( f"Klient {row['Klient']} został zlecony " f"{date_only} " f"i nie został jeszcze ukończony.\n" ) f.write(message) print(f"Messages for {email} written to messages_{email.replace('@', '_')}.txt") # Save the combined DataFrame to the main CSV file. all_data_df.to_csv("combined_scraped_data.csv", index=False) print("All data saved to combined_scraped_data.csv") # Run the function10 function10()In this corrected version:
- Fixed the indentation in the conditional blocks within the loop that processes table rows.
- The row counter logic counts all occurrences and properly appends the first unique instance with the count of duplicates.
This should resolve the indentation errors and meet your requirement of counting all duplicates while only adding the count to the first instance of each unique row.