# html-to-freq-3.py
# create sorted dictionary of word-frequency pairs
url = 'https://www.dhi.ac.uk/api/data/oldbailey_record_single?idkey=t17800628-33'
text = getTextFromAPI(url)

fullwordlist = stripNonAlphaNum(text)
wordlist = removeStopwords(fullwordlist, stopwords)
dictionary = wordListToFreqDict(wordlist)
sorteddict = sortFreqDict(dictionary)

# compile dictionary into string:
outstring = ""
for key,value in sorteddict:
    outstring += value + ": " + str(key) + "\n"
print(outstring)

# obo.py library

stopwords = ['a', 'about', 'above', 'across', 'after', 'afterwards']
stopwords += ['again', 'against', 'all', 'almost', 'alone', 'along']
stopwords += ['already', 'also', 'although', 'always', 'am', 'among']
stopwords += ['amongst', 'amoungst', 'amount', 'an', 'and', 'another']
stopwords += ['any', 'anyhow', 'anyone', 'anything', 'anyway', 'anywhere']
stopwords += ['are', 'around', 'as', 'at', 'back', 'be', 'became']
stopwords += ['because', 'become', 'becomes', 'becoming', 'been']
stopwords += ['before', 'beforehand', 'behind', 'being', 'below']
stopwords += ['beside', 'besides', 'between', 'beyond', 'bill', 'both']
stopwords += ['bottom', 'but', 'by', 'call', 'can', 'cannot', 'cant']
stopwords += ['co', 'computer', 'con', 'could', 'couldnt', 'cry', 'de']
stopwords += ['describe', 'detail', 'did', 'do', 'done', 'down', 'due']
stopwords += ['during', 'each', 'eg', 'eight', 'either', 'eleven', 'else']
stopwords += ['elsewhere', 'empty', 'enough', 'etc', 'even', 'ever']
stopwords += ['every', 'everyone', 'everything', 'everywhere', 'except']
stopwords += ['few', 'fifteen', 'fifty', 'fill', 'find', 'fire', 'first']
stopwords += ['five', 'for', 'former', 'formerly', 'forty', 'found']
stopwords += ['four', 'from', 'front', 'full', 'further', 'get', 'give']
stopwords += ['go', 'had', 'has', 'hasnt', 'have', 'he', 'hence', 'her']
stopwords += ['here', 'hereafter', 'hereby', 'herein', 'hereupon', 'hers']
stopwords += ['herself', 'him', 'himself', 'his', 'how', 'however']
stopwords += ['hundred', 'i', 'ie', 'if', 'in', 'inc', 'indeed']
stopwords += ['interest', 'into', 'is', 'it', 'its', 'itself', 'keep']
stopwords += ['last', 'latter', 'latterly', 'least', 'less', 'ltd', 'made']
stopwords += ['many', 'may', 'me', 'meanwhile', 'might', 'mill', 'mine']
stopwords += ['more', 'moreover', 'most', 'mostly', 'move', 'much']
stopwords += ['must', 'my', 'myself', 'name', 'namely', 'neither', 'never']
stopwords += ['nevertheless', 'next', 'nine', 'no', 'nobody', 'none']
stopwords += ['noone', 'nor', 'not', 'nothing', 'now', 'nowhere', 'of']
stopwords += ['off', 'often', 'on','once', 'one', 'only', 'onto', 'or']
stopwords += ['other', 'others', 'otherwise', 'our', 'ours', 'ourselves']
stopwords += ['out', 'over', 'own', 'part', 'per', 'perhaps', 'please']
stopwords += ['put', 'rather', 're', 's', 'same', 'see', 'seem', 'seemed']
stopwords += ['seeming', 'seems', 'serious', 'several', 'she', 'should']
stopwords += ['show', 'side', 'since', 'sincere', 'six', 'sixty', 'so']
stopwords += ['some', 'somehow', 'someone', 'something', 'sometime']
stopwords += ['sometimes', 'somewhere', 'still', 'such', 'system', 'take']
stopwords += ['ten', 'than', 'that', 'the', 'their', 'them', 'themselves']
stopwords += ['then', 'thence', 'there', 'thereafter', 'thereby']
stopwords += ['therefore', 'therein', 'thereupon', 'these', 'they']
stopwords += ['thick', 'thin', 'third', 'this', 'those', 'though', 'three']
stopwords += ['three', 'through', 'throughout', 'thru', 'thus', 'to']
stopwords += ['together', 'too', 'top', 'toward', 'towards', 'twelve']
stopwords += ['twenty', 'two', 'un', 'under', 'until', 'up', 'upon']
stopwords += ['us', 'very', 'via', 'was', 'we', 'well', 'were', 'what']
stopwords += ['whatever', 'when', 'whence', 'whenever', 'where']
stopwords += ['whereafter', 'whereas', 'whereby', 'wherein', 'whereupon']
stopwords += ['wherever', 'whether', 'which', 'while', 'whither', 'who']
stopwords += ['whoever', 'whole', 'whom', 'whose', 'why', 'will', 'with']
stopwords += ['within', 'without', 'would', 'yet', 'you', 'your']
stopwords += ['yours', 'yourself', 'yourselves']


def stripTags(pageContents):
    startLoc = pageContents.find("<p>")
    endLoc = pageContents.rfind("<br/>")

    pageContents = pageContents[startLoc:endLoc]

    inside = 0
    text = ''

    for char in pageContents:
        if char == '<':
            inside = 1
        elif (inside == 1 and char == '>'):
            inside = 0
        elif inside == 1:
            continue
        else:
            text += char

    return text

# Get the text from an Old Bailey Online API request
def getTextFromAPI(url):
    from urllib.request import urlopen
    response = urlopen(url)
    import json
    text = json.loads(response.read().decode('utf-8'))['hits']['hits'][0]['_source']['text']
    return text

# Given a text string, remove all non-alphanumeric
# characters (using Unicode definition of alphanumeric).

def stripNonAlphaNum(text):
    import re
    return re.compile(r'\W+', re.UNICODE).split(text)
    
# Given a list of words, return a dictionary of
# word-frequency pairs.

def wordListToFreqDict(wordlist):
    wordfreq = [wordlist.count(p) for p in wordlist]
    return dict(zip(wordlist,wordfreq))
    
# Sort a dictionary of word-frequency pairs in
# order of descending frequency.

def sortFreqDict(freqdict):
    aux = [(freqdict[key], key) for key in freqdict]
    aux.sort()
    aux.reverse()
    return aux

# Given a list of words, remove any that are
# in a list of stop words.

def removeStopwords(wordlist, stopwords):
    return [w for w in wordlist if w not in stopwords]

# Given a URL, return string of lowercase text from page.

def webPageToText(url):
    from urllib.request import urlopen
    response = urlopen(url)
    html = response.read().decode('utf-8')
    text = stripTags(html).lower()
    return text

# Given name of calling program, a url and a string to wrap,
# output string in html body with basic metadata and open in Firefox tab.

def wrapStringInHTMLMac(program, url, body):
    import datetime
    from webbrowser import open_new_tab

    now = datetime.datetime.today().strftime("%Y%m%d-%H%M%S")
    filename = program + '.html'
    f = open(filename,'w')

    wrapper = """<html>
    <head>
    <title>%s output - %s</title>
    </head>
    <body><p>URL: <a href=\"%s\">%s</a></p><p>%s</p></body>
    </html>"""

    whole = wrapper % (program, now, url, url, body)
    f.write(whole)
    f.close()

    #Change the filepath variable below to match the location of your directory
    filename = 'file:///Users/username/Desktop/programming-historian/' + filename

    open_new_tab(filename)
    
# Given name of calling program, a url and a string to wrap,
# output string in html body with basic metadata
# and open in Firefox tab.

def wrapStringInHTMLWindows(program, url, body):
    import datetime
    from webbrowser import open_new_tab

    now = datetime.datetime.today().strftime("%Y%m%d-%H%M%S")

    filename = program + '.html'
    f = open(filename,'w')

    wrapper = """<html>
    <head>
    <title>%s output - %s</title>
    </head>
    <body><p>URL: <a href=\"%s\">%s</a></p><p>%s</p></body>
    </html>"""

    whole = wrapper % (program, now, url, url, body)
    f.write(whole)
    f.close()

    open_new_tab(filename)

# Given a list of words and a number n, return a list
# of n-grams.

def getNGrams(wordlist, n):
    return [wordlist[i:i+n] for i in range(len(wordlist)-(n-1))]
    
# Given a list of n-grams, return a dictionary of KWICs,
# indexed by keyword.

def nGramsToKWICDict(ngrams):
    keyindex = len(ngrams[0]) // 2

    kwicdict = {}

    for k in ngrams:
        if k[keyindex] not in kwicdict:
            kwicdict[k[keyindex]] = [k]
        else:
            kwicdict[k[keyindex]].append(k)
    return kwicdict

# Given a KWIC, return a string that is formatted for
# pretty printing.

def prettyPrintKWIC(kwic):
    n = len(kwic)
    keyindex = n // 2
    width = 10

    outstring = ' '.join(kwic[:keyindex]).rjust(width*keyindex)
    outstring += str(kwic[keyindex]).center(len(kwic[keyindex])+6)
    outstring += ' '.join(kwic[(keyindex+1):])

    return outstring