alistscrap.py

import requests
import urllib.request
import time
from bs4 import BeautifulSoup
from lxml import html
import requests
import urllib
import numpy as np
import pandas as pd

f = open("win1.html")
document= BeautifulSoup(f.read())
Pitches = []
names = []
Names = []
AngelLinks = []
companies = []
signal = []
market = []
website = []
size = []
Market_New = []
div1 =  document.findAll('div', {'class':'base startup'})
for i in div1:
    Name = i.findAll('div', {'class':'name'})
    names.append(Name)

    Company = i.findAll('div', {'class':'pitch'})
    companies.append(Company)

    Market = i.findAll('div', {'class':'market'})
    market.append(Market)

    Website = i.findAll('div', {'class':'website'})
    website.append(Website)

    Size = i.findAll('div', {'class':'column company_size hidden_column'})

for i in companies:
    if len(str(i[0].text)) == 0:
        Pitches.append('No Pitch Available')
    else:
        Pitches.append(i[0].text)    # PITCHES AVAILABLE

for i in names:
    Names.append(i[0].text)        # COMPANIES NAMES AVAILABLE
    
Market = []
for i in market:
    Market.append(i[0].text)        # MARKET DISCRIPTION AVAILABLE

Website = []
for i in website:
    z = (i[0].findAll('a'))
    Website.append(z[0].text)

Data = [[Names], [Pitches], [Market], [Website]]
D_data = pd.DataFrame(Data)

#D_data.to_csv('D1_data.csv')
data = {'Company': Names, 'Market':Market, 'Pitches': Pitches, 'Website': Website}
D2 = pd.DataFrame(data)

D2.to_csv('D2.csv')