ops

#!/usr/bin/env python
# -*- coding: utf-8 -*-

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from bs4 import BeautifulSoup
import re
import requests
import pandas as pd
from tabulate import tabulate
import os
import csv

f = csv.writer(open('ops.csv', 'w', encoding='utf-8'))
f.writerow(['Name', 'Link'])

pages = []

for i in range(1, 146):
    url = 'https://www.kompetenznetz-mittelstand.de/de/app/account/list/public?s=IwvKhoY3u236pAafN&action=list&page=' + str(i) + '&item_count=200'
    pages.append(url)


for item in pages:
    page = requests.get(item)
    soup = BeautifulSoup(page.text, 'html.parser')

    img_tag = soup.img
    soup.img.decompose()
    img_tag

    frist_links = soup.find(class_='sf-nav sf-nav-tabmenu sf-hide-print')
    frist_links.decompose()

    left_links = soup.find(class_='left')
    left_links.decompose()

    last_links = soup.find(class_='sf-btn-group left')
    last_links.decompose()

    last_links2 = soup.find(class_='sf-btn-group')
    last_links2.decompose()

    company_list = soup.find(class_='sfsDialogContent')

    company_item_list = company_list.find_all('a')

    for company_name in company_item_list:
        names = company_name.contents[0]
        links = 'https://www.kompetenznetz-mittelstand.de' + company_name.get('href')
        f.writerow([names, links])

writer = csv.writer(open('correct.csv', 'w', encoding='utf-8'))
for row in csv.reader('ops.csv'):
    if not row[0].startswith('<img alt'):
        writer.writerow(row)