import json
from lxml import html
import re
import requests

FILENAME_HINT_XPATH = "../preceding-sibling::p[1]/strong/text()"

def code_for_post(site, post):
    r = requests.get('https://api.stackexchange.com/2.1/posts/{1}?site={0}&filter=withbody'.format(site, post))
    j = json.loads(r.text)
    body = j['items'][0]['body']
    tree = html.fromstring(body)

    code_elements = tree.xpath("//pre/code[%s]" % (FILENAME_HINT_XPATH))
    return dict((c.xpath(FILENAME_HINT_XPATH)[0], c.findtext(".")) for c in code_elements)

def write_files(code):
    extension = '.java'     # <-- Yuck, due to @Simon.
    for filename_hint, content in code.iteritems():
        filename = re.sub(r'[^A-Za-z0-9]', '', filename_hint) + extension
        with open(filename, 'w') as f:
            print >>f, content

write_files(code_for_post('codereview', 41198))

import json
from lxml import html
import re
import requests

FILENAME_HINT_XPATH = "../preceding-sibling::p[1]/strong/text()"

def code_for_post(site, post):
    r = requests.get('https://api.stackexchange.com/2.1/posts/{1}?site={0}&filter=withbody'.format(site, post))
    j = json.loads(r.text)
    body = j['items'][0]['body']
    tree = html.fromstring(body)

    code_elements = tree.xpath("//pre/code[%s]" % (FILENAME_HINT_XPATH))
    return dict((c.xpath(FILENAME_HINT_XPATH)[0], c.findtext(".")) for c in code_elements)

def write_files(code):
    extension = '.java'     # <-- Yuck, due to @Simon.
    for filename_hint, content in code.iteritems():
        filename = re.sub(r'[^A-Za-z0-9]', '', filename_hint) + extension
        with open(filename, 'w') as f:
            print >>f, content

write_files(code_for_post('codereview', 41198))

I would encourage you to produce more explicit output, particularly with the filenames. If I wanted to reverse the process and scrape the code into files on my machine, using a Python script such as the following…

import json
from lxml import html
import re
import requests

FILENAME_HINT_XPATH = "../preceding-sibling::p[1]/strong/text()"

def code_for_post(site, post):
    r = requests.get('https://api.stackexchange.com/2.1/posts/{1}?site={0}&filter=withbody'.format(site, post))
    j = json.loads(r.text)
    body = j['items'][0]['body']
    tree = html.fromstring(body)

    code_elements = tree.xpath("//pre/code[%s]" % (FILENAME_HINT_XPATH))
    return dict((c.xpath(FILENAME_HINT_XPATH)[0], c.findtext(".")) for c in code_elements)

def write_files(code):
    extension = '.java'     # <-- Yuck, due to @Simon.
    for filename_hint, content in code.iteritems():
        filename = re.sub(r'[^A-Za-z0-9]', '', filename_hint) + extension
        with open(filename, 'w') as f:
            print >>f, content

write_files(code_for_post('codereview', 41198))

… then I would have to make assumptions about the filename extension.

I would encourage you to produce more explicit output, particularly with the filenames. If I wanted to reverse the process and scrape the code into files on my machine, using a Python script such as the following…

import json
from lxml import html
import re
import requests

FILENAME_HINT_XPATH = "../preceding-sibling::p[1]/strong/text()"

def code_for_post(site, post):
    r = requests.get('https://api.stackexchange.com/2.1/posts/{1}?site={0}&filter=withbody'.format(site, post))
    j = json.loads(r.text)
    body = j['items'][0]['body']
    tree = html.fromstring(body)

    code_elements = tree.xpath("//pre/code[%s]" % (FILENAME_HINT_XPATH))
    return dict((c.xpath(FILENAME_HINT_XPATH)[0], c.findtext(".")) for c in code_elements)

def write_files(code):
    extension = '.java'     # <-- Yuck, due to @Simon.
    for filename_hint, content in code.iteritems():
        filename = re.sub(r'[^A-Za-z0-9]', '', filename_hint) + extension
        with open(filename, 'w') as f:
            print >>f, content

write_files(code_for_post('codereview', 41198))

… then I would have to make assumptions about the filename extension.

The invocation method could be improved. Instead of hard-coding a particular directory to look in for the source files, I would suggest…

• If files are explicitly passed to the program as command-line arguments, use those files.
• If a directory is specified, then use all files contained therein, excluding files with significant non-ASCII content.
• If no command-line arguments are used, then operate on the current directory.

It would be nice to be able to say java ReviewPreparer *.java | pbcopy.