Created
April 3, 2017 16:33
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import urllib,urllib.request | |
import lxml.html | |
from io import StringIO, BytesIO | |
import json | |
import re | |
import subprocess | |
import os | |
import tempfile | |
def main( url=None, show_json=False, show_img_urls=False ) : | |
req = urllib.request.Request(url=url) | |
f = urllib.request.urlopen(req) | |
page = f.read().decode('utf-8') | |
doc = lxml.html.parse(StringIO(page)) | |
title = doc.xpath('//title/text()')[0] | |
json_data_link = doc.xpath('//link[@rel="alternate"][@type="application/json+oembed"]')[0] | |
pdf_link = doc.xpath('//*[@id="share_pdf"]')[0] | |
req = urllib.request.Request(url= json_data_link.attrib['href']) | |
f = urllib.request.urlopen(req) | |
str = f.read().decode('utf-8') | |
obj = json.load( StringIO( str ) ) | |
if show_json : | |
print( json.dumps(obj) ) | |
exit(0) | |
title = obj["title"] | |
author = obj["author_name"] | |
iframe = obj["html"] | |
doc = lxml.html.parse(StringIO(iframe)) | |
src = 'http:'+(doc.xpath('//iframe/@src'))[0] | |
id = os.path.basename(urllib.parse.urlparse(src).path) | |
req = urllib.request.Request(url= src) | |
f = urllib.request.urlopen(req) | |
str = f.read().decode('utf-8') | |
doc = lxml.html.parse(StringIO(str)) | |
src = doc.xpath('//head//script[contains(./text(), "var talk")]')[0] | |
src = src.text | |
data = re.search( re.compile('var talk\s?=\s?({.+});'), src).group(1) | |
if show_img_urls : | |
print( data ) | |
exit(0) | |
data = json.load( StringIO( data ) ) | |
urls = [] | |
for p in data['slides'] : | |
urls.append( p['original'] ) | |
old_wd = os.getcwd() | |
os.chdir( tempfile.mkdtemp() ) | |
print( os.getcwd() ) | |
cmd = "xargs -P5 -I@ curl -sLJO @ " | |
p = subprocess.Popen(cmd.strip().split(" "), stdin=subprocess.PIPE) | |
for (index,url) in enumerate(urls) : | |
p.stdin.write(('%s\n' % url ).encode('utf8')) | |
p.stdin.close() | |
p.wait() | |
cmd = "convert slide*.jpg out.pdf " | |
p = subprocess.Popen(cmd, shell=True ) | |
p.wait() | |
content = open('out.pdf', 'rb').read() | |
cmd = "rm *.jpg *.pdf " | |
p = subprocess.Popen(cmd, shell=True ) | |
p.wait() | |
tmp = os.getcwd() | |
os.chdir( old_wd ) | |
os.removedirs(tmp) | |
f_name = '%s - %s.pdf' % ( title.replace("/",'|'), author.replace("/",'|') ) | |
open( f_name , 'wb').write(content) | |
if __name__ == '__main__' : | |
import argparse | |
parser = argparse.ArgumentParser(description=u'SpeakerDeckからデータ取ってくる') | |
parser.add_argument( '-j ', '--json', action="store_true", help=u'jsonデータ取得') | |
parser.add_argument( '-i ', '--imgs', action="store_true", help=u'スライド画像URL一覧') | |
parser.add_argument('urls', metavar='URLs', type=str, nargs='+', help='対象の URL ') | |
args = parser.parse_args() | |
for url in vars(args)['urls'] : | |
main( url, show_json=vars(args)["json"], show_img_urls=vars(args)['imgs']) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment