Created
April 15, 2018 14:29
-
-
Save RamonYeung/d44336016e69b227669fe2fd6293d9f9 to your computer and use it in GitHub Desktop.
Automatically Download IJCAI 2017 Accepted Papers with customized keywords
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
import requests | |
import re | |
from urllib.request import urlopen | |
import multiprocessing as mp | |
import os | |
def process(pair): | |
idx, title = pair | |
idx = '0' * (4 - len(idx)) + idx | |
for word in keywords: | |
if word in title.lower(): | |
print(idx, title) | |
file_name = '../data/%s.pdf' % idx | |
with urlopen(pdf % idx) as response, open(file_name, 'wb') as f: | |
f.write(response.read()) # bytes obj | |
# pdf integrity checking, can be done manually. | |
with open(file_name, 'wb') as f: | |
if not len(f.read()): | |
print('broken file', file_name, 'try to download it again ...') | |
# repeat | |
with urlopen(pdf % idx) as response, open(file_name, 'wb') as g: | |
f.write(response.read()) | |
break | |
url = 'https://www.ijcai.org/proceedings/2017/' | |
pdf = 'https://www.ijcai.org/proceedings/2017/%s.pdf' | |
keywords = ['knowledge', 'reason', 'question', 'answer', 'relation', 'entity', 'ontolo', 'embed'] | |
regex = re.compile(r'<div id="paper([0-9]+)" class="paper_wrapper"><div class="title">(.*?)</div>') | |
r = requests.get(url) | |
content = re.findall(regex, r.text) | |
if not os.path.exists('../data'): | |
os.mkdir('../data') | |
print('Creating directory "data/" for papers ...') | |
with mp.Pool(10) as p: | |
p.map(process, content) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment