OxFess_top_post_scraper.py

import facebook
import requests
import time

start_time = time.time()

graph = facebook.GraphAPI(access_token="your token here", version="2.7")

# Gets the number of reacts on a post with id post_id
def getReactCount(post_id):
    return graph.get_object(id=post_id, fields='reactions.limit(0).summary(true)') \
    [u'reactions'][u'summary'][u'total_count']

# Get the oxfess page
page = graph.get_object(id="oxfess")

target = raw_input("Enter a file to store the info of the most reacted to posts: ")

# Then get the first batch of 100 posts
posts = graph.get_connections(id=page[u'id'], connection_name='posts', limit=100)

# Use this to store final post ids and reaction counts
allpostdata = []

# The number of processed posts
postcount = 0

trip = True

# Until we can get no more posts
while(True):
    try:
        print 'Fetching post batch ' + str(postcount) + ' to ' + str(postcount + 100)
        i = 0
        for post in posts['data']:
            print 'Fetching post number ' + str(i) + ' of the batch'
            i+=1
            allpostdata.append((post['id'], getReactCount(post['id'])))
        postcount+=100

        # Attempt to make a request to the next page of data, if it exists.
        posts=requests.get(posts['paging']['next']).json()
    except KeyError:
        # When there are no more pages (['paging']['next']), break from the
        # loop and end the script.
        break

print 'Posts have been collected. Sorting...'

allpostdata.sort(key = lambda x: x[1])

print 'Processed ' + str(postcount) + 'posts and found these ids for the 10 most reacted posts: '

bestposts = allpostdata[-10:]
print bestposts

with open(target, 'w') as f:
    for i, post in enumerate(bestposts):
        message = graph.get_object(id=post[0])["message"]
        f.write("Post number " + str(10-i) + ":\n")
        f.write(message.encode('utf-8'))
        f.write("\n")
        f.write("id: " + str(post[0]) + '\n')
        f.write("Reaction count: " + str(post[1]) + '\n')
        f.write("\n\n\n")


print 'Running time: ' + str(time.time() - start_time)