acrymble

#create URLs for search results pages and save the files
def getSearchResults(query, kwparse, fromYear, fromMonth, toYear, toMonth, entries):
    
    import urllib2
    
    startValue = 0
    #determine how many files need to be downloaded.
    pageCount = entries / 10
    remainder = entries % 10
    if remainder > 0:

acrymble

#download-searches.py
import obo

query = 'mulatto*+negro*'

obo.getSearchResults(query, "advanced", "1700", "00", "1750", "99", 13)

acrymble

def getSearchResults(query, kwparse, fromYear, fromMonth, toYear, toMonth):
    
    import urllib2
    
    startValue = 0
    
    #each part of the URL. Split up to be easier to read.
    url = 'http://www.oldbaileyonline.org/search.jsp?foo=bar&form=searchHomePage&_divs_fulltext='
    url += query
    url += '&kwparse=' + kwparse

acrymble

#download-searches.py
import obo

query = 'mulatto*+negro*'

obo.getSearchResults(query, "advanced", "1700", "00", "1750", "99")

acrymble

http://www.oldbaileyonline.org/browse.jsp?id=t17160113-18&div=t17160113-18&terms=mulatto|negro#highlight

acrymble

mulatto*+negro*

acrymble

def getIndivTrials(query):
    import os

    dirPath = #add the path to your 'programming-historian' directory here
    #for PC it should start with: 'C:\\Documents and Settings...'
    #for Mac it should start with: '/Users/...'

    searchResults = os.listdir(dirPath + query)

    print searchResults

acrymble

def getIndivTrials(query):
    #...
    urls = []
    for files in searchResults:
        if files.find("search-result") != -1:
            f = open(query + "/" + files, 'r')
            text = f.read().split(" ")
            f.close()
            
            for words in text:

acrymble

def getIndivTrials(query):
    import os, urllib2, time

    #import built-in python functions for building file paths
    from os.path import join as pjoin

    #find the search results pages in the new directory.
    dirPath = #add the path to your 'programming-historian' directory here
    #for PC it should start with: 'C:\\Documents and Settings...'
    #for Mac it should start with: '/Users/...'

acrymble

#download-searches.py
import obo

query = 'mulatto*+negro*'

obo.getSearchResults(query, "advanced", "1700", "00", "1750", "99", 13)

obo.getIndivTrials(query)