miaou

from bs4 import BeautifulSoup

import requests
import csv

urldepart = "http://ww w.f f -  v oy a nc e.c om/"

visitedUrl = set()
urlToVisit = [urldepart]

with open('eggs.csv', 'w', newline='') as csvfile:
    spamwriter = csv.writer(csvfile, delimiter=',')

    def lit_page(url):
        global visitedUrl
        global spamwriter
        global urlToVisit
        print(".")
        r  = requests.get(url)
        visitedUrl.add(url)
        data = r.text

        soup = BeautifulSoup(data)

        for link in soup.find_all('a'):
            urlHref=link.get('href')
            
            if urlHref is not None and urlHref not in visitedUrl and (urlHref[0]=='.' or urlHref[0]=='/' or urlHref.startswith(urldepart)):
                if urlHref[0]=='.' or urlHref[0]=='/':
                    urlToVisit.append(urldepart+urlHref)
                else:
                    urlToVisit.append(urlHref)

        for link in soup.find_all('div'):
            classe=link.get('class')
            
            if classe is not None and 'post' in classe and 'row' in classe and 'panel' in classe:
                for link2 in link.find_all('div'):
                    classe2=link2.get('class')
                    if "postbody" in classe2 :
                        member = None
                        content = None
                        for link3 in link2.find_all('p'):
                            classe3=link3.get('class')
                            if "author" in classe3:
                                count=0
                                for link4 in link3.find_all('a'):
                                    if count>0:
                                        member=link4.get_text()
                                    count=count+1
                        if member is not None:
                            for link3 in link2.find_all('div'):
                                classe3=link3.get('class')
                                if "content" in classe3:
                                    content=link3.get_text()
                            spamwriter.writerow([url,member,content])
        
            
    for url in urlToVisit:
        lit_page(url)