reclosedev/books_info.py Secret

## books_info.py
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import urllib

import jinja2
import lxml.html
import requests

try:
    import requests_cache
    requests_cache.configure("livelib")
except ImportError:
    pass

BOOK_FOLDER = ur"d:\tmp\books\Все книги в формате FB2\\"
FIND_URL = "http://www.livelib.ru/find/"


def find_book_info(book_name):
    quoted_name = urllib.quote_plus(book_name.encode("utf-8"))
    r = requests.get(FIND_URL + quoted_name)
    doc = lxml.html.fromstring(r.content)
    doc.make_links_absolute(FIND_URL)
    div_info = doc.cssselect("div.bookinfo")
    if not div_info:
        return  {"info": book_name,
                 "description": "NOT FOUND"}
    div_info = div_info[0]
    description = div_info.getparent().getnext()
    description.tag = "div"
    return {"info": lxml.html.tostring(div_info,
                                       encoding="utf8").decode("utf8"),
            "description": lxml.html.tostring(description,
                                              encoding="utf8").decode("utf8")}


def generate_report(filename, groups):
    env = jinja2.Environment(loader=jinja2.FileSystemLoader("."))
    template = env.get_template("output_template.html")
    stream = template.stream(groups=groups)
    stream.dump(open(filename, "wb"), "utf-8")


def main():
    groups = []
    for dirpath, dirnames, filenames in os.walk(BOOK_FOLDER):
        group = dirpath.replace(BOOK_FOLDER, "")
        print group
        books = []
        for filename in filenames:
            if not filename.endswith(".fb2"):
                continue
            name, ext = os.path.splitext(filename)
            year, name = name.split(" ", 1)
            book = find_book_info(name)
            book["year"] = year
            book["name"] = name
            book["filename"] = filename
            books.append(book)
        if books:
            groups.append({"name": group, "books": books})
    generate_report("books.html", groups)


if __name__ == "__main__":
    main()

## output_template.html
<!DOCTYPE html>
<html xmlns="http://www.w3.org/1999/html">
<head>
  <meta charset="utf-8">
  <title>Книги — победители премий</title>
    <link rel="stylesheet" type="text/css" href="http://s.livelib.ru/css/style.css" />
    <style>
      body {margin: 3% 10%}
    </style>
</head>
<body>
<p>
<a href="http://rutor.org/torrent/248905/">Раздача с книгами</a> <br>
<a href="https://gist.github.com/reclosedev/bf58c122d3c8eb47787d">Скрипт на Python 2.7 (зависимости: requests, lxml, jinja2)</a>
</p>
{% for group in groups %}
  <h2>{{ group.name }}</h2>
  <table style="width: 100%">
    {% for book in group.books %}
        <tr><td colspan="2">{{ book.year }}</td></tr>
        <tr>
            <td>{{ book.info }}</td>
            <td>{{ book.description }}</td>
        </tr>
        <tr><td colspan="2" style="border: none"><hr></td></tr>
    {% endfor %}
  </table>
  <br>
{% endfor %}
</body>
</html>
	#!/usr/bin/env python
	# -- coding: utf-8 --
	import os
	import urllib

	import jinja2
	import lxml.html
	import requests

	try:
	import requests_cache
	requests_cache.configure("livelib")
	except ImportError:
	pass

	BOOK_FOLDER = ur"d:\tmp\books\Все книги в формате FB2\\"
	FIND_URL = "http://www.livelib.ru/find/"


	def find_book_info(book_name):
	quoted_name = urllib.quote_plus(book_name.encode("utf-8"))
	r = requests.get(FIND_URL + quoted_name)
	doc = lxml.html.fromstring(r.content)
	doc.make_links_absolute(FIND_URL)
	div_info = doc.cssselect("div.bookinfo")
	if not div_info:
	return {"info": book_name,
	"description": "NOT FOUND"}
	div_info = div_info[0]
	description = div_info.getparent().getnext()
	description.tag = "div"
	return {"info": lxml.html.tostring(div_info,
	encoding="utf8").decode("utf8"),
	"description": lxml.html.tostring(description,
	encoding="utf8").decode("utf8")}


	def generate_report(filename, groups):
	env = jinja2.Environment(loader=jinja2.FileSystemLoader("."))
	template = env.get_template("output_template.html")
	stream = template.stream(groups=groups)
	stream.dump(open(filename, "wb"), "utf-8")


	def main():
	groups = []
	for dirpath, dirnames, filenames in os.walk(BOOK_FOLDER):
	group = dirpath.replace(BOOK_FOLDER, "")
	print group
	books = []
	for filename in filenames:
	if not filename.endswith(".fb2"):
	continue
	name, ext = os.path.splitext(filename)
	year, name = name.split(" ", 1)
	book = find_book_info(name)
	book["year"] = year
	book["name"] = name
	book["filename"] = filename
	books.append(book)
	if books:
	groups.append({"name": group, "books": books})
	generate_report("books.html", groups)


	if __name__ == "__main__":
	main()
	<!DOCTYPE html>
	<html xmlns="http://www.w3.org/1999/html">
	<head>
	<meta charset="utf-8">
	<title>Книги — победители премий</title>
	<link rel="stylesheet" type="text/css" href="http://s.livelib.ru/css/style.css" />
	<style>
	body {margin: 3% 10%}
	</style>
	</head>
	<body>
	<p>
	<a href="http://rutor.org/torrent/248905/">Раздача с книгами</a> <br>
	<a href="https://gist.github.com/reclosedev/bf58c122d3c8eb47787d">Скрипт на Python 2.7 (зависимости: requests, lxml, jinja2)</a>
	</p>
	{% for group in groups %}
	<h2>{{ group.name }}</h2>
	<table style="width: 100%">
	{% for book in group.books %}
	<tr><td colspan="2">{{ book.year }}</td></tr>
	<tr>
	<td>{{ book.info }}</td>
	<td>{{ book.description }}</td>
	</tr>
	<tr><td colspan="2" style="border: none"><hr></td></tr>
	{% endfor %}
	</table>
	<br>
	{% endfor %}
	</body>
	</html>