Scripts for Python Programs to Start Digging Into JSTOR’s Early Journals

journal_list.py

# PROGRAM NAME: journal_list.py

# Displays the title of every journal in the JSTOR Early Journal Content Data Bundle.
# Highlights those with "Psych" or "Philos" in the title (+ two general science journals).
# Displays the filename of the first article for each journal. 

# Written by Christopher D Green
# January 2014

# Modified by (if you modify this program, put your name here.)
# Date Modified (if you modify this program, put the date of the modification here.)

#START OF PROGRAM
import os #You need to import this in order to read the filenames from the disk below.

#Below is the directory path to where I am keeping the files on my computer.
#You will need to change it to suit your own system.
dirname='/Users/chriso/Desktop/JSTOR-journals/bundle/' 

#Puts list of filename in the variable "filenames"
filenames=os.listdir(dirname) 

#Initializing a few variables.
contents=''; title=''; lasttitle1=''; lasttitle2=''; lasttitle3=''; i=0


for i in range(len(filenames)):                   #Looping through each file...
    if filenames[i]!='.DS_Store':                 #Don't read this file (which causes Python to crash)
        filename=dirname+filenames[i]             #Create the full path to ech file
        file=open(filename,'r', encoding='utf-8') #Open the file for reading (in unicode)
        contents=file.read()                      #Put the entire contents of the file in a variable called "contents"  
        file.close()                              #Close the file (so you don't overwrite it later)
        if '<journaltitle>' in contents:             #If the file comes from a journal... 
            start=contents.find('<journaltitle>')+14 #Find the start of the journal's title
            end=contents.find('</journaltitle>')     #Find the end of the journal's title
            title=contents[start:end]                #Put everything in between in a variable called "title"
            #First, check that you haven't seen this title recently
            if title!=lasttitle1 and title!=lasttitle2 and title!=lasttitle3: 
                #Then, check if the journal title is one of those in which you are particularly interested. 
                if 'Psych' in title or 'Philos' in title or 'Monist' in title or title=='Science' or 'Scientific Monthly' in title:
                    print()
                    print('***',title, filenames[i][8:]) #If it is, highlight the title on the screen.
                    print()
                else:
                    print(title, filenames[i][8:])       #Display other journal title on the screen too.
                lasttitle3=lasttitle2                    #Move your recently-seen titles up the line. 
                lasttitle2=lasttitle1
                lasttitle1=title


#END OF PROGRAM

move_psychphil.py

#PROGAM NAME: move_psychphil.py (ver 1.0)

# Extracts article titles, author names, volume numbers, and page numbers
# for Psych, Philos, and some science journals in the JSTOR EARLY JOURNAL
# CONTENT DATA BUNDLE. Displays these on screen and creates file names to
# copy them to their own folder (but does not actually do the copying). 
# Also creates .csv list of articles from The Monist only.

# Written by Christopher D Green
# January 2014
# Modified April 2014 to not move files, but just list their original file names in the Excel file.

# START PROGRAM
import os #needed to navigate directory tree of resident harddisk

#set from and to directories
fromdirname='/Users/chriso/Desktop/JSTOR-journals/bundle/'
todirname='/Users/chriso/Desktop/JSTOR-journals/temp/'

#read filenames from directory
filenames=os.listdir(fromdirname)                 

#initialize some variables
contents=''; title=''; lasttitle1=''; lasttitle2=''; lasttitle3=''; i=0
jnum=-1; volnum='0'; pnum='0'

#setting up csv file that lists authors, titles, etc. for Phil Review articles
listfile=open(todirname+'Monist.csv', 'w') 
listfile.write('year,vol,page,author,title\n')    
listfile.close
    
#list of desired journals and the abbreviations to be used in filenames
journals=[['The Journal of Philosophy, Psychology and Scientific Methods',
                'The Philosophical Review', 'The Monist'],
                ['JPPSM','PhilRev','Monist']]
#other interesting journals: The American Journal of Psychology, Science,
#     The Scientific Monthly, The Journal of Speculative Philosophy
                
for i in range(len(filenames)):
    if filenames[i]!='.DS_Store':
        filename=fromdirname+filenames[i]
        #print(filenames[i])
        file=open(filename,'r', encoding='utf-8')
        contents=file.read()
        file.close()
        if '<journaltitle>' in contents: 
            start=contents.find('<journaltitle>')+14   #find start of journal title
            end=contents.find('</journaltitle>')       #find end of journal title
            jtitle=contents[start:end]                 #get journal title
        if jtitle in journals[0]:                      #is it one of the journal I want?
            jnum=journals[0].index(jtitle) 
            typeloc=contents.find('<type>')            #is it a full article?
            if contents[typeloc+6:typeloc+9]=='fla':
                #print ('.', end='')
                print(jtitle)
                volstart=contents.find('<volume>')+8   #find start of volume number
                volend=contents.find('</volume>')      #find end of volume number
                volnum=contents[volstart:volend]       #get volume number

                pstart=contents.find('<fpage>')+7      #find start of page number
                pend=contents.find('</fpage>')         #find end of page number
                pnum=contents[pstart:pend]             #get initial page number

                yearstart=contents.find('<year>')+6    #find start of year
                year=contents[yearstart:yearstart+4]   #get volume number


                atitlestart=contents.find('<title>')+7 #find start of article title
                atitleend=contents.find('</title>')    #find end of article title
                atitle=contents[atitlestart:atitleend] #get article
                while ',' in atitle:
                    commaloc=atitle.find(',')          #find commmas in atitle...
                    atitle=atitle[:commaloc]+'`'+atitle[commaloc+1:] #...replace with `
                print(atitle)

                authorstart=contents.find('<authors>\n    <list-item>')+25 #find start of author's name
                authorend=''; k=0; author=''               #finding the end of the author's name is a little more complex.
                while '<' not in author:                   #the < marks the </list-item> tag at the end of the 1st author's name
                    author=author+contents[authorstart+k]  #accumulate author's name character by character
                    k=k+1                                  #ideally, we would like to list all authors. Haven't done that here.
                author=author[:-1]                         #removes the < at the end of the author's name
                if author=='P. C.':
                    author='Paul Carus'

                revauthor='';k=1;                          #putting lastname first
                while len(author)-k>=0 and author[len(author)-k] != ' ': #finding the space 
                    k=k+1                                  #between the first & last names 
                lastname=author[len(author)-k+1:]
                lastname.lower(); lastname.capitalize()    #setting Lastname
                firstname=author[:len(author)-k+1]         #(if it was all CAPS)
                firstname.lower(); firstname.capitalize()  #setting Firstname
                #Occasionally names come out all in CAPS anyway. Check by hand.
                revauthor=lastname+firstname

                while ' ' in revauthor: #removing spaces 
                    spaceloc=revauthor.find(' ')
                    revauthor=revauthor[:spaceloc]+revauthor[spaceloc+1:]
                while '.' in revauthor:  #removing dots
                    dotloc=revauthor.find('.')
                    revauthor=revauthor[:dotloc]+revauthor[dotloc+1:]
                #This process still fails on names with Jr. at the end.
                #These must be corrected by hand at present. 

                if len(author) < 3:
                    revauthor='NoAuthor'
                print(author)
                
                #assemble name of file to which article will be saved
                outfilename=journals[1][jnum]+'.'+volnum+'.'+pnum+'.txt'
                fullpathname=todirname+outfilename
                #print(fullpathname)
                print()

                fullpath=open(fullpathname, 'w', encoding='utf-8') #writes files to a new directory
                fullpath.write(contents)
                fullpath.close()
                #print ('*', end='')

                if jtitle=='The Monist':     #Creates csv list of Monist articles
                    listfile=open(todirname+'Monist.csv', 'a', encoding='utf-8')
                    listfile.write(filenames[i]+','+year+','+volnum+','+pnum+','+revauthor+','+atitle+','+outfilename+'\n')
                    listfile.close()
                if jtitle=='The Journal of Philosophy, Psychology and Scientific Methods':     #Creates csv list of JPPSM articles
                    listfile=open(todirname+'JPPSM.csv', 'a', encoding='utf-8')
                    listfile.write(filenames[i]+','+year+','+volnum+','+pnum+','+revauthor+','+atitle+','+outfilename+'\n')
                    listfile.close()
                if jtitle=='The Philosophical Review':     #Creates csv list of Phil Rev articles
                    listfile=open(todirname+'PhilRev.csv', 'a', encoding='utf-8')
                    listfile.write(filenames[i]+','+year+','+volnum+','+pnum+','+revauthor+','+atitle+','+outfilename+'\n')
                    listfile.close()


                    
# END PROGRAM