In [1]:

    

!pip install PyPDF2
import urllib
import PyPDF2


    

    




Requirement already satisfied: PyPDF2 in /home/staeiou/anaconda3/lib/python3.6/site-packages

In [41]:

    

pr = PyPDF2.PdfFileReader("/home/staeiou/github/cscw-pages/data/pdfs/2013/p203-thayer.pdf")


    

    




PdfReadWarning: Xref table not zero-indexed. ID numbers for objects will be corrected. [pdf.py:1736]






    
Out[41]:





11

In [28]:

    

import re
import os
import glob

rxcountpages = re.compile(r"/Type\s*/Page([^s]|$)", re.MULTILINE|re.DOTALL)

def count_pages(filename):
    with open(filename,"rb") as f:
        data = f.read()
    return len(rxcountpages.findall(data))


    

In [ ]:

    




    

In [42]:

    

cscw_len = {}
years = [2008,2010,2011,2012,2013,2014,2015,2016,2017]
for year in years:
    
    cscw_len[year] = []
    for filename in glob.glob("/home/staeiou/github/cscw-pages/data/pdfs/" + str(year) + "/*.pdf"):
        pr = PyPDF2.PdfFileReader(filename)
        pages = len(pr.pages)
        cscw_len[year].append(pages)


    

    




PdfReadWarning: Xref table not zero-indexed. ID numbers for objects will be corrected. [pdf.py:1736]

In [48]:

    

import pandas as pd
pd.DataFrame(cscw_len[2013]).describe()


    

    
Out[48]:






  

    

      

      
0
    
  
  

    

      
count
      
141.000000
    
    

      
mean
      
10.687943
    
    

      
std
      
2.384877
    
    

      
min
      
1.000000
    
    

      
25%
      
10.000000
    
    

      
50%
      
11.000000
    
    

      
75%
      
12.000000
    
    

      
max
      
17.000000
    
  

In [ ]: