import urllib.request
import traceback
import re
import time
from bs4 import BeautifulSoup

def isCurrentYear(dateStr):
    return re.search("(1[2-9]mon)|(20(0|1)[^7])", dateStr) is None

def writePostCount(postCount, filename):
        input_filename=open(filename, "w")
        for (k,v) in postCount.items():
               input_filename.write(k+":"+str(v)+"\n")
        input_filename.close()
        return filename

postCount = {}
forums = ["590", "29", "642", "665", "44", "538"]
for forum in forums:
    forum_pageNum = 1
    forum_isCurrentYear = True
    while forum_isCurrentYear:
        forum_urlstr = "https://epicmafia.com/forum/"+forum+"?page="+str(forum_pageNum)
        print("Scanning "+forum_urlstr+"...")
        while True:
            try:
                with urllib.request.urlopen(forum_urlstr) as forum_url:
                    forum_page = forum_url.read()
            except urllib.error.HTTPError:
                continue
            break
        forum_soup = BeautifulSoup(forum_page, "html.parser")
        forum_soup.prettify("latin-1")
        threads = forum_soup.find_all(name="a", class_="topic-title")
        for thread in threads:
            lastpost = thread.parent.parent.parent.find(class_="lastpost").find(class_="sg").text
            #print(lastpost)
            if not isCurrentYear(lastpost):
                forum_isCurrentYear = False
                break
            #continue
            thread_pageNum = -1
            while True:
                thread_urlstr = "https://epicmafia.com"+thread.get("href")+("" if thread_pageNum==-1 else ("?page="+str(thread_pageNum)))
                while True:
                    try:
                        with urllib.request.urlopen(thread_urlstr) as thread_url:
                            thread_page = thread_url.read()
                    except urllib.error.HTTPError:
                        continue
                    break
                thread_soup = BeautifulSoup(thread_page, "html.parser")
                thread_soup.prettify("latin-1")
                posts = thread_soup.find_all(class_="postuser")
                print("Scanning "+thread_urlstr+"...")
                for post in posts:
                    userlink = post.find(name="a", class_="tt")
                    created_at = post.find(class_="created_at").text
                    #print(created_at)
                    if not isCurrentYear(created_at):
                        continue
                    if userlink is None: #deleted user
                        continue
                    username = userlink.text
                    if username not in postCount:
                        postCount[username] = 0
                    postCount[username] += 1
                    #print(username)
                if thread_soup.find(class_="pagenav") is None:
                    break
                thread_pageNum = int(thread_soup.find(class_="pagenav").find(class_="selected").contents[0].text)
                if thread_pageNum==1:
                    break
                thread_pageNum -= 1
        forum_pageNum += 1
writePostCount(postCount, "test.txt")