Sherlock.py

import requests
from bs4 import BeautifulSoup


""" Example of use:
    This will look into "A Study in Scarlet" for the 3rd paragraph, 1st line, 2nd word

    ```
    from sherlock import find_word


    find_word("asis", 3, 1, 2)
    ```

"""




BASE_URL = "https://sherlock-holm.es"

data = {}
data["A Study In Scarlet"] = "/stories/html/stud.html"
data["The Sign of the Four"] = "/stories/html/sign.html"
data["The Hound of the Baskervilles"] = "/stories/html/houn.html"
data["The Valley of Fear"] = "/stories/html/vall.html"
data["A Scandal in Bohemia"] = "/stories/html/scan.html"
data["The Red-Headed League"] = "/stories/html/redh.html"
data["A Case of Identity"] = "/stories/html/iden.html"
data["The Boscombe Valley Mystery"] = "/stories/html/bosc.html"
data["The Five Orange Pips"] = "/stories/html/five.html"
data["The Man with the Twisted Lip"] = "/stories/html/twis.html"
data["The Adventure of the Blue Carbuncle"] = "/stories/html/blue.html"
data["The Adventure of the Speckled Band"] = "/stories/html/spec.html"
data["The Adventure of the Engineer's Thumb"] = "/stories/html/engr.html"
data["The Adventure of the Noble Bachelor"] = "/stories/html/nobl.html"
data["The Adventure of the Beryl Coronet"] = "/stories/html/bery.html"
data["The Adventure of the Copper Beeches"] = "/stories/html/copp.html"
data["Silver Blaze"] = "/stories/html/silv.html"
data["Yellow Face"] = "/stories/html/yell.html"
data["The Stockbroker's Clerk"] = "/stories/html/stoc.html"
data["The Gloria Scott"] = "/stories/html/glor.html"
data["The Musgrave Ritual"] = "/stories/html/musg.html"
data["The Reigate Puzzle"] = "/stories/html/reig.html"
data["The Crooked Man"] = "/stories/html/croo.html"
data["The Resident Patient"] = "/stories/html/resi.html"
data["The Greek Interpreter"] = "/stories/html/gree.html"
data["The Naval Treaty"] = "/stories/html/nava.html"
data["The Final Problem"] = "/stories/html/fina.html"
data["The Empty House"] = "/stories/html/empt.html"
data["The Norwood Builder"] = "/stories/html/norw.html"
data["The Dancing Men"] = "/stories/html/danc.html"
data["The Solitary Cyclist"] = "/stories/html/soli.html"
data["The Priory School"] = "/stories/html/prio.html"
data["Black Peter"] = "/stories/html/blac.html"
data["Charles Augustus Milverton"] = "/stories/html/chas.html"
data["The Six Napoleons"] = "/stories/html/sixn.html"
data["The Three Students"] = "/stories/html/3stu.html"
data["The Golden Pince-Nez"] = "/stories/html/gold.html"
data["The Missing Three-Quarter"] = "/stories/html/miss.html"
data["The Abbey Grange"] = "/stories/html/abbe.html"
data["The Second Stain"] = "/stories/html/seco.html"
data["Wisteria Lodge"] = "/stories/html/wist.html"
data["The Cardboard Box"] = "/stories/html/card.html"
data["The Red Circle"] = "/stories/html/redc.html"
data["The Bruce-Partington Plans"] = "/stories/html/bruc.html"
data["The Dying Detective"] = "/stories/html/dyin.html"
data["Lady Frances Carfax"] = "/stories/html/lady.html"
data["The Devil's Foot"] = "/stories/html/devi.html"
data["His Last Bow"] = "/stories/html/last.html"


def initials(story):
    str = ""
    for w in story.split(' '):
        str += w[0].lower();

    return str

def fetch_word(link, p, l, w):
    p -= 1
    l -= 1
    w -= 1

    r = requests.get(BASE_URL + link)
    soup = BeautifulSoup(r.text, 'html.parser')

    # If there is a table of contents is a novel, otherwise its a short story
    # and in the novels, there is an extra paragraf
    if soup.find('.table-of-contents'):
        p += 1


    paragraph = soup.find_all('p')[p].text
    line = paragraph.split('.')[l].strip()
    word = line.split(' ')[w]

    return word

def find_word(story, par, line, word):
        for story_name, link in data.items():
            if story.lower() == initials(story_name):
                print(story_name, '=>', fetch_word(link, par, line, word))