from urllib import urlopen
import re
import sys

channel = raw_input('Enter vimeo channel: ')
pageNum = raw_input('Enter number of follower pages to scrape:')
pageNum = int(pageNum)
adjList = open(channel+'.csv', 'w') #create csv


for i in range(1, pageNum + 1):
    print >> sys.stderr, 'Scraping page '+str(i)+'...'

    url = urlopen('http://vimeo.com/channels/'+channel+'/followers/page:'+str(i)+'/sort:datefollow')
    htmltext = url.read()
    pattern = re.compile('a href="/user(.+?)"')
    userIds = re.findall(pattern, htmltext)



    for i in range(len(userIds)):
        #standard request - http://vimeo.com/api/v2/username/request.output
        apiRequest = urlopen('http://vimeo.com/api/v2/user'+userIds[i]+'/channels.json')
        userJsonData = apiRequest.read()

        pattern = re.compile(',"name":"(.+?)"')
        channelNames = re.findall(pattern, userJsonData)
        for j in range(len(channelNames)):  #remove commas and whitespace
            channelNames[j] = channelNames[j].replace(' ', '_')
            channelNames[j] = channelNames[j].replace(',', '')



        #Write userId and channel to csv using a comma as delimiter
        for j in range(len(channelNames)):
            try:
                adjList.write('user'+userIds[i]+ ', '+ channelNames[j]+'\n')
            except BaseException, e:
                print >> sys.stderr, 'Error:', str(e)



adjList.close()
print >> sys.stderr, 'Done writing. '+channel+'.csv saved to script folder.'