O'Reilly free ebooks downloader

omercy.py

'''
O'Meirrcy !!!! Download free ebooks from O'Reilly

Usage:
> git clone  https://gist.github.com/Krazybug/1ae50814d25b0a1d862dfdf7161ee503
> mv 1ae50814d25b0a1d862dfdf7161ee503 omercy
> cd omercy
> pip install requests
> pip install bs4
> python omercy.py

You will get 1 directory per book under the dir oreilly-free-ebooks containing:
- 1 .json file with a small descrition (title, author, links to ebooks file, ...)
- 1 cover file (jpg, jpe, gif, ...)
- all files in the formats availables for the book (pdf, epub, mobi)
... 
Enjoy :)
'''

'''
   DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE 
                    Version 2, December 2004 

 Copyright (C) 2004 Sam Hocevar <[email protected]> 

 Everyone is permitted to copy and distribute verbatim or modified 
 copies of this license document, and changing it is allowed as long 
 as the name is changed. 

            DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE 
   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION 

  0. You just DO WHAT THE FUCK YOU WANT TO.
'''

import os
import sys
import shutil
import json
import mimetypes
import requests
from bs4 import BeautifulSoup
from urllib.parse import urlparse
from functools import reduce
from tempfile import tempdir

source = "http://www.oreilly.com/free/reports.html"
extensions = ["epub", "pdf", "mobi"]
# If you're not interested in some ebook format, just remove it there, for instance:
# extensions = ["epub", "pdf"]

print("-"*50)
print("Grabbing from", source)
print("-"*50)
print()

try:
    req = requests.get(source)
    req.raise_for_status()
except:
    print("Unable to open source url:", source)
    sys.exit(1)
home_s = BeautifulSoup(req.content, "html.parser")

# Get description of the books
topics = {}
topics_s = home_s.find_all("section")
for topic in topics_s:
    topics[topic.attrs["id"]] = topic.find(class_="btn see-more").attrs["href"]
# Extra "data" section
topics["data1"] = "http://www.oreilly.com/data/free/archive.html"
print("Topics:", ", ".join(topics.keys()))


count_books = 0

# Some books are not available for free (or without inscription ?)
unreachable_files = [
    "http://shop.oreilly.com/product/0636920022916.do",
    "http://shop.oreilly.com/product/0636920025580.do",
    "http://shop.oreilly.com/product/0636920026082.do",
    "http://shop.oreilly.com/product/0636920033127.do?intcmp=il-web-free-product-lgen_webplatform",
    "http://shop.oreilly.com/product/0636920039303.do?intcmp=il-web-free-product-lgen_ydkjs_upgoing"
]

# These files don't respect the rules and have to be handled explicitly
explicit_files = {
    "http://www.oreilly.com/free/css-secrets-collection?intcmp=il-web-free-product-lgen_css_secrets": {
        "pdf": "http://cdn.oreillystatic.com/oreilly/pdfs/CSS_Secrets_sample-3.pdf"
    },
    "http://www.oreilly.com/free/transforms-in-css.csp?intcmp=il-web-free-product-lgen_csstransforms": {
        "pdf": "http://www.oreilly.com/web-platform/free/files/Transforms_in_CSS.pdf",
        "epub": "http://www.oreilly.com/web-platform/free/files/Transforms_in_CSS.epub",
        "mobi": "http://www.oreilly.com/web-platform/free/files/Transforms_in_CSS.mobi"
    },
    "http://www.oreilly.com/data/free/data-and-finance.csp":
    {
        "pdf": "http://www.oreilly.com/data/free/files/data-money-regulation.pdf",
        "epub": "http://www.oreilly.com/data/free/files/data-money-regulation.epub",
        "mobi": "http://www.oreilly.com/data/free/files/data-money-regulation.mobi"
    },
    "http://www.oreilly.com/data/free/business-models-for-the-data-economy.csp?intcmp=il-data-free-lp-lgen_free_reports_page":
    {
        "pdf": "http://www.oreilly.com/data/free/files/business-models-for-data-economy.pdf",
        "epub": "http://www.oreilly.com/data/free/files/business-models-for-data-economy.epub",
        "mobi": "http://www.oreilly.com/data/free/files/business-models-for-data-economy.mobi"
    },
    "http://www.oreilly.com/data/free/data-analytics-in-sports.csp":
    {
        "pdf": "http://www.oreilly.com/data/free/files/Data_Analytics_in_Sports.pdf",
        "epub": "http://www.oreilly.com/data/free/files/Data_Analytics_in_Sports.epub",
        "mobi": "http://www.oreilly.com/data/free/files/Data_Analytics_in_Sports.mobi"
    },
    "http://www.oreilly.com/data/free/data-technology-future-of-play.csp?intcmp=il-data-free-lp-lgen_free_reports_page":
    {
        "pdf": "http://www.oreilly.com/data/free/files/data-technology-and-the-future-of-play.pdf",
        "epub": "http://www.oreilly.com/data/free/files/data-technology-and-the-future-of-play.epub",
        "mobi": "http://www.oreilly.com/data/free/files/data-technology-and-the-future-of-play.mobi"
    }
}

prefix="oreilly-free-ebooks"

for name, url in topics.items():
    print()
    print("-"*50)
    print("Parsing topic:", name)
    print()

    try:
        req = requests.get(url)
        req.raise_for_status()
    except:
        print("Unable to open topic page:", url)
        continue
    topics_s = BeautifulSoup(req.content, "html.parser")

    for book_s in topics_s.find_all(attrs={"data-toggle": "popover"}):
        # Check if book description already exists
        b_url = book_s.attrs["href"]

        if b_url in unreachable_files:
            print()
            print("Unreachable file => ignored", b_url)
            count_books += 1
            print("-->", count_books, "Book description(s) considered")
            continue

        print()
        print("Parsing book:", b_url)

        filename = urlparse(b_url).path.replace(".csp", "").split('/')[-1]
        filepath = prefix+"/"+filename+"/"+filename+".json"
        print("Checking book information:", filepath)

        if os.path.isfile(filepath):
            print("Book information is already present...")
            count_books = count_books+1
            print("-->", count_books, "Book description(s)")
        else:
            # Get book description
            print("No existing data => retrieving in file:", filepath)
            book = {}
            book["topic"] = name if name != "data1" else "data"
            book["title"] = book_s.attrs["title"]
            book["description"] = book_s.attrs["data-content"]
            b_url = book_s.attrs["href"]
            # Some books urls don't have "http:" prefix
            b_url = b_url if b_url.startswith("http:") else "http:"+b_url
            book["source"] = b_url
            c_url = book_s.find("img").attrs["src"]
            c_url = c_url if c_url.startswith("http:") else "http:"+c_url
            book["cover"] = c_url
            # Get extra information (author, author bio, isbn, ...)
            try:
                req = requests.get(b_url)
                req.raise_for_status()
            except:
                print("Unable to open book extra informations page:", b_url)
                continue
            else:
                ext_book_s = BeautifulSoup(req.content, "html.parser")
                if not len(req.history):  # not redirected
                    author = ext_book_s.find("h3", class_="author-name")
                    if author:
                        book["author"] = author.getText()
                    author_bio = ext_book_s.find("div", class_="highlight")
                    if author_bio:
                        book["author_bio"] = author_bio.find("p").getText()
                else:  # redirect on Safari ?
                    author = ext_book_s.find("div", class_="t-authors")
                    if author:
                        book["author"] = author.getText().split("by ")[1]
                    isbn = ext_book_s.find("div", class_="t-isbn")
                    if isbn:
                        book["isbn"] = isbn.get_text().split("ISBN: ")[1]

            # files with explicit download urls are not explored
            if b_url in explicit_files.keys():
                for ext in extensions:
                    if ext in explicit_files[b_url]:
                        book[ext] = explicit_files[b_url][ext]
            else:
                # Outside of a navigator, download links are not displayed (javascript code)
                # Books download url template is "http://www.oreilly.com/"+book["topic"]+"/free/files/"+filename+"?download=true"
                # However, we can get the ebooks formats available to avoid useless domnloads (Error 404)
                d_url = book["source"].split("?")[0]+"?download=true"
                try:
                    req = requests.get(d_url)
                    req.raise_for_status()
                except:
                    print("Unable to open book download page", d_url)

                # We handle books without any topic in their description url but with a topic in their download url
                if book["source"].startswith("http://www.oreilly.com/free"):
                    t = book["source"].split("?topic=")[-1]
                    filebase = "http://www.oreilly.com/"+t+"/free/files/"+filename
                # The nominal case
                # filebase="http://www.oreilly.com/"+book["topic"]+"/free/files/"+filename
                else:
                    filebase = book["source"].split(
                        filename)[0]+"files/"+filename

                download_s = BeautifulSoup(req.content, "html.parser")
                c_formats = 0
                for ext in extensions:
                    if download_s.find("a", class_="btn "+ext):
                        book[ext] = filebase+"."+ext
                        c_formats = c_formats+1
                # When the description page is redirected on Safari, the formats aren't displayed,
                # we have to try to download each of them
                if not c_formats:
                    print("No format directly available", d_url)
                    for ext in extensions:
                        book[ext] = filebase+"."+ext
            # Persists json data
            os.makedirs(os.path.dirname(filepath), exist_ok=True)
            with open(filepath, 'w') as fd:
                json.dump(book, fd)
            print("Book description(s) retrieved:", b_url)

            count_books += 1
            print("-->", count_books, "Book description(s) considered")

# Get covers
print()
print("-"*50)
print("Retrieving covers")

for path, dirs, files in os.walk(prefix):
    for dir in dirs:
        print()
        filebase = path+"/"+dir+"/"+dir
        print(filebase)
        jsonfile = filebase+".json"
        try:
            book = json.load(open(jsonfile))
        except:
            print("Unable to get information:", jsonfile)
            continue

        cover_u = book["cover"]
        print("Retrieving", cover_u)

        try:
            req = requests.get(cover_u)
            req.raise_for_status()
        except:
            print("Unable to retrieve cover:", cover_u)
        else:
            content_type = req.headers['content-type']
            ext = mimetypes.guess_extension(content_type)
            filename = path+"/"+dir+"/cover"+ext
            if os.path.isfile(filename):
                print(filename, "already exists...")
            else:
                with open(filename+".tmp", 'wb') as fd:
                    fd.write(req.content)
                shutil.move(filename+".tmp", filename)
                print(filename, "retrieved...")

# Get books
count_files = 0
for ext in extensions:
    print()
    print("-"*50)
    print("Retrieving books:", ext)

    for path, dirs, files in os.walk(prefix):
        for dir in dirs:
            print()
            filebase = path+"/"+dir+"/"+dir
            print(filebase)

            jsonfile = filebase+".json"
            try:
                book = json.load(open(jsonfile))
            except:
                print("Unable to get information:", jsonfile)
                continue

            filename = filebase+"."+ext
            if os.path.isfile(filename):
                print(filename, "already exists...")
                count_files = count_files+1
                print("-->", count_files, "file(s) considered")
            else:
                if not ext in book:
                    continue
                book_u = book[ext]
                print("Retrieving", book_u)
                # assuming that the "content-type" is correct
                try:
                    req = requests.get(book_u)
                    req.raise_for_status()
                except requests.exceptions.HTTPError as err:
                    print("Unable to retrieve file:", book_u)
                    print("source=", book["source"])
                    print("Http Error:", err)
                    book.pop(ext)
                    with open(filebase+".json", 'w') as fd:
                        json.dump(book, fd)
                        print("Book description(s) updated:", book_u)
                except:
                    print("Unexpected error:", book_u)
                else:
                    with open(filename+".tmp", 'wb') as fd:
                        fd.write(req.content)
                    shutil.move(filename+".tmp", filename)
                    print(filename, "retrieved...")

                    count_files = count_files+1
                    print("-->", count_files, "file(s) considered")

# Summary of operations
count_books = count_files = 0
count_formats = {}
for ext in extensions:
    count_formats[ext] = 0
for path, dirs, files in os.walk(prefix):
    for dir in dirs:
        count_books += 1
        filebase = path+"/"+dir+"/"+dir
        for ext in extensions:
            if os.path.isfile(filebase+"."+ext):
                count_formats[ext] += 1
count_files = reduce(lambda a, b: a + b, count_formats.values())

print()
print("--------> Total books count:", count_books)
print("----------> Total files count:", count_files)
for ext in extensions:
    print(
        "--------------> Total {0} files count: {1}".format(ext, count_formats[ext]))