#wouf 2020 (py3.6.4)
#http://site2wouf.fr
#Pour créer dico.txt
#Qui contient un lexique basé sur
#ODS8
#En scollant le site : listesdemots.net
#requis :l beautifulsoup4
#(cmd : pip install beautifulsoup4)
#requis :2 requests
#(cmd : pip install requests)
import requests
from bs4 import BeautifulSoup
fichier = open("dico_anglais.txt", "w")
fichier.close()
#   Initialisation:
url="https://www.bestwordlist.com/allwords"
requete = requests.get(str(url+".htm")) #page1
print(requete.url)
page = requete.content
soup = BeautifulSoup(page,features="html5lib")

span=soup.find_all("span",{"class":["mot","mot2"]})

for s in span:
    fichier = open("dico_anglais.txt", "a")
    #debug=input(s)
    mots=s.string.strip()
    lesmots=mots.split(" ")
    for l in lesmots:
        fichier.write(l+"\n")
        
    
 
   
    fichier.close()
#page 2 à 918:
for i in range(2,542):

    lurl=url+"page"+str(i)+".htm"
    ok=False
    while not ok:
        try:
            requete = requests.get(lurl,timeout=1)
            ok=True
        except:
            print("Problème de connexion. Je recommence !")
    print(requete.url)
    page = requete.content
    soup = BeautifulSoup(page,features="html5lib")
    
    span=soup.find_all("span",{"class":["mot","mot2"]})
    for s in span:
        fichier = open("dico_anglais.txt", "a")
        
        mots=s.string.strip()
        
        lesmots=mots.split(" ")
        
        for l in lesmots:
            fichier.write(l+"\n")
        fichier.close()
#fin du script