amazon.py

import sys
import google
import time
import random
from bs4 import BeautifulSoup
import urllib.request
import http.cookiejar
from selenium import webdriver
import subprocess
import blessings
from operator import itemgetter

browser = webdriver.Firefox()
# import Resource
topic = input("Topic: ").replace(" ", "+")


t = blessings.Terminal()

amz_base = "https://www.amazon.com/s/?url=search-alias%3Dstripbooks&field-keywords="


browser.get(amz_base + topic)

change_default_format = input("Default format is paperback. Change? ")
if not change_default_format:
    browser.find_element_by_partial_link_text("Paperback").click()

pages_to_search = int(input("Pages to search? (About 10-12 books per page) "))

amz_links = set()


for i in range(pages_to_search):

    titles = browser.find_elements_by_class_name("s-access-detail-page")

    for title in titles:
        title_url = title.get_attribute('href').split('/ref', 1)[0]
        print(title_url)
        amz_links.add(title_url)

    time.sleep(5)
    browser.execute_script("window.scrollTo(0, document.body.scrollHeight);")

    try:
        browser.find_element_by_partial_link_text('Next Page').click()
    except:
        break


print("Total books links: " + str(len(amz_links)))

books = list()

time.sleep(5)

count = 0

for book_url in amz_links:

    count += 1
    print(str(count) + " of " + str(len(amz_links)))

    book = dict()
    print(book_url)
    browser.get(book_url)
    #book['title'] = browser.find_element_by_id('productTitle').text
    #print("Title: " + book['title'])
    use = input("Use book? ")
    if not use:
        continue

    book['url'] = book_url
    title = browser.find_element_by_id('productTitle').text
    print("TITLE: " + title)
    truncate_at = input("TRUNCATE: ")
    if not truncate_at:
        book['title'] = title
    else:
        book['title'] = title.split(truncate_at, 1)[0]
    print("TITLE TO USE: " + book['title'])

    authors = browser.find_elements_by_class_name('author')
    author_names = list()

    for author in authors:

        name = author.text

        if "(Author)" not in name:
            continue

        name = name.split(' (Au', 1)[0]

        author_names.append(name)

    num_of_authors = len(author_names)

    author_string = ""

    if ( num_of_authors == 1 ):
        author_string = author_names[0]
    else:
        for i in range(len(author_names)):
            last_name = author_names[i].split(' ', -1)[-1]
            print("Original: " + author_names[i] + "\n"
                "Last Name: " + last_name
            )
            fix_last_name = input("Fix last name: ")
            if not fix_last_name:
                author_names[i] = last_name
            else:
                author_names[i] = fix_last_name



    if ( num_of_authors == 2):
        author_string = author_names[0] + " and " + author_names[1]

    if ( num_of_authors == 3):
        author_string = author_names[0] + ", " + author_names[1] + ", and " + author_names[2]

    if ( num_of_authors > 3):
        author_string = author_names[0] + " et al."

    print(author_string)

    book['author'] = author_string

    details_element = browser.find_element_by_xpath("//*[contains(text(), 'Product Details')]")

    browser.execute_script("return arguments[0].scrollIntoView();", details_element)

    book['year'] = input("Publication year: ")

    book['description'] = input("Description: ")

    book_string = " - [_{title}_]({url}) ({year}), by {author}, {description}\n".format(**book)

    print(t.yellow(book_string))

    book['string'] = book_string

    books.append(book)


for book in books:
    print(book['string'])