Trying to export data taken from HTML using beautiful soup-CodePudding

I'm trying to extract information from the HTML texts that I get from URLs that I create from a For loop and then use beautiful soup.

I get to isolate the information correctly but when I'm trying to export the data I get an error message "All arrays must be of the same length"

weblink = []
filing_type = []
company_name = []
date = []


#Importing file
df = pd.read_csv('Downloads\Dropped_Companies.csv')
#Getting companie's names into list
companies_column=list(df.columns.values)[4]
name_ = df[companies_column].tolist()
#Formatting company's names for creating URLs
for CompanyName in name_:
    company_name.append(CompanyName.lower().replace(" ",'_'))
company_name

for item in range(0, len(company_name)):
    link = 'https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&company='   company_name[item]   '&type=10-K&dateb=&owner=exclude&count=100'
       
    #Getting the HTML text
    headers = random.choice(headers_list)
    r = requests.Session()
    r.headers = headers
    html = r.get(link).text

    #Calling beautiful soup for better HTML text
    soup = bs.BeautifulSoup(html)
    tet_ = soup.find_all("a", id = "documentsbutton") 
      
    #Get the links 
    for link in tet_:
        weblink.append('https://www.sec.gov'   link.get('href'))
        test11 = soup.find_all("table", class_= "tableFile2")
        
    for link in test11:
        row = link.find_all("td", nowrap  = "nowrap")
        for i in range(0, len(row), 3):
            filing_type.append(row[i].getText())
            date.append(link.find("td", class_ = "small").find_next_sibling("td").text)
            name.append(company_name[item])


data = {'Company Name':name,'Filing Date': date,'Filing Type':filing_type,"Weblink":weblink}
outputdf = pd.DataFrame(data)
outputdf.to_csv('Downloads/t_10KLinks.csv')

CodePudding user response：

data = {'Company Name':name,'Filing Date': date,'Filing Type':filing_type,"Weblink":weblink}
outputdf = pd.DataFrame.from_dict(data, orient='index')
outputdf.to_csv('Downloads/t_10KLinks.csv')

pandas.DataFrame.from_dict documentation.