import requests
import matplotlib.pyplot as plt
from wordcloud import WordCloud
from bs4 import BeautifulSoup
import time

def processPostsPage(pageNumber, userId):
    
    #grab the next page of posts
    pageUrl = "https://bitcointalk.org/index.php?action=profile;u=" + str(userId) + ";sa=showPosts;start="+str(pageNumber*20)
    response = requests.get(pageUrl)
    data = response.content  
    
    #grab divs with the 'post' attribute
    soup = BeautifulSoup(data)
    postsOnPage = soup.findAll("div", { "class" : "post" })
    
    #return an array of word clouds
    wordCloudsForPageOfPosts = []
    
    count = 1;
    
    stopwords = ["post","posts"]
    
    #convert posts to wordcloud images
    for div in postsOnPage:
    
        text = div.get_text()
        
        #remove the stopwords with a little magic
        text = " ".join([word for word in text.split() if word not in stopwords])
        
        nextCloud = WordCloud().generate(text)
        
        wordCloudsForPageOfPosts.append(nextCloud)
        
        count = count+1
        
    return wordCloudsForPageOfPosts
 

def buildPlot(userId, numberOfPosts):
    width = 25
    height = 15
    fig = plt.figure(figsize=(width,height))

    
    currentPage = 1
    
    count = 0
    
    while(count <= numberOfPosts):
        
        #sleep in between grabbing pages of posts for a stress free bitcointalk crawl
        time.sleep(1)
        
        #grab the clouds for that page
        clouds = processPostsPage(currentPage,userId)
        
        #display the clouds until we reach the right number
        for cloud in clouds:
            count = count+1
            if(count < numberOfPosts):
                a = fig.add_subplot(5,5,count)
                
                #hack to delete tick marks
                for a in fig.get_axes():
                    a.set_xticks([])
                    a.set_yticks([])
                a.set_title("Post " + str(count))
                plt.imshow(cloud)
            
            
userID = 249526
numberOfPostToDisplay = 25
buildPlot(userID, numberOfPostToDisplay)
plt.show()