0

I'm trying to write an output as a csv file and getting this error:

write_file
    df_data.to_csv('output.txt', sep='|')
AttributeError: 'list' object has no attribute 'to_csv'

When I change my output type to the others (excel or html), I get the same error as well.

Here's my code being used:

from bs4 import BeautifulSoup
import requests
import pandas as pd
import re


def main():
    certs_url = "https://csrc.nist.gov/projects/cryptographic-module-validation-program/validated-modules/search/all"

    # Data refresh from the NIST site
    data = get_html(certs_url)
    cmvp_data = get_cmvp_data(data)
    write_file('txt', cmvp_data)


def get_html(url):
    # make request to URL and convert to BS obj
    req = requests.get(url)
    soup = BeautifulSoup(req.content, 'html.parser')
    return soup


def get_cmvp_data(cmvp_content):
    detail_urls_lst = []
    sunset_date_lst = []
    # --- Build CMVP dataframe ---
    search_tbl = cmvp_content.find_all('table', id='searchResultsTable')
    # convert HTML table to df obj
    cert_table = pd.read_html(str(search_tbl))
    df = cert_table[0]
    #print(cert_table)
    # column headers - sub spaces w/'_'
    df.columns = [column.replace(" ", "_") for column in df.columns]
    #print(df.columns)


    #print(df['Module_Name'][0])
    # --- Filter tech ---
    df_filtered = df.loc[(df['Vendor_Name'].str.contains('Splunk', case=False, na=False)) |
                df['Vendor_Name'].str.contains('Trend Micro', case=False, na=False) |
                df['Vendor_Name'].str.contains('Yubico', case=False, na=False) |
                df['Vendor_Name'].str.contains('Red Hat', case=False, na=False) |
                df['Vendor_Name'].str.contains('Palo Alto', case=False, na=False) |
                df['Vendor_Name'].str.contains('Microsoft', case=False, na=False) |
                df['Vendor_Name'].str.contains('Cisco', case=False, na=False)]
    #print(df_filtered['Module_Name'])

    for i in df['Certificate_Number']:
        print(i)


    return detail_urls_lst


def write_file(output_type, df_data,):
    # -- Write file --
    if output_type == 'txt':
        # df to txt
        df_data.to_csv('output.txt', sep='|')
    elif output_type == 'excel':
        # write to excel
        df_data.to_excel('output.xlsx')
    else:
        # write df to html file
        result = df_data.to_html()
        func = open('df.html', 'w')
        func.write(result)
        func.close()
    print('Export complete')
    return


if __name__ == "__main__":
    main()

I tried looking at posts for similar errors and wasn't able to figure out a solution to fix this error. This is my first time using pandas and just can't figure out what's causing this.

Craicerjack
  • 6,203
  • 2
  • 31
  • 39
Mitchell Privett
  • 77
  • 1
  • 7
  • 2
    `to_csv` is a dataframe method and youre calling it on a list (in `get_cmvp_data` you changed your dataframe to a list) - https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.to_csv.html – Craicerjack Sep 01 '22 at 18:35
  • After this line ```cmvp_data = get_cmvp_data(data)``` , what is the output of this: ```print(type(cmvp_data))```? Its should be a list type as returned by get_cvmp_data function. And list has no method: ```to_csv```, its a dataframe method. However, you can loop over the list and write it excel/csv line by line by following [this](https://stackoverflow.com/questions/37289951/how-to-write-to-a-csv-line-by-line) or you can use Method 1 from [this link](https://www.geeksforgeeks.org/python-save-list-to-csv/). – saad_saeed Sep 01 '22 at 18:44
  • change `return detail_urls_lst` to `return df_filtered` or `df` – NoobVB Sep 01 '22 at 19:28

0 Answers0