Download WASET conference abstracts

download-waset.py

#!/usr/bin/env python3
#
# Copyright (c) 2018 Hyeshik Chang
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.
#

from urllib.request import urlopen, Request
from urllib.error import HTTPError
import time
import bsddb3
import random
import sys
import numpy as np


class WasetAbstractRetriever:

    FIRST_ABSTRACT_NUMBER = 0
    LAST_ABSTRACT_NUMBER = 100000 # Change this when there're more updates

    DELAY_DURATIONS = [1, 2, 4, 5] # Randomly chosen
    JSON_URL_FORMAT = 'https://waset.org/Publications/XML?abstract={number}&t=json'
    STATUS_PERIOD = 25
    HTTP_HEADER = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) '
            'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
    }

    def __init__(self, dbfile):
        self.db = bsddb3.hashopen(dbfile, 'c')
        self.abstract_numbers = self.initiate_article_ids()

    def initiate_article_ids(self):
        artids = []
        for nid in range(self.FIRST_ABSTRACT_NUMBER, self.LAST_ABSTRACT_NUMBER):
            if str(nid).encode() not in self.db:
                artids.append(nid)

        random.shuffle(artids)

        print('=> {0} abstracts to go ({1} done)'.format(len(artids), len(self.db)))
        return artids

    def retrieve_article(self, artid):
        dbkey = str(artid).encode()
        url = self.JSON_URL_FORMAT.format(number=artid)
        if dbkey in self.db:
            return

        req = Request(url, data=None, headers=self.HTTP_HEADER)

        try:
            print('--> Retrieving', artid, end='\t')
            sys.stdout.flush()
            self.db[dbkey] = urlopen(req).read()
        except HTTPError as err:
            self.db[dbkey] = 'HTTP{}'.format(err.code).encode()
            print('-', err.code)
        else:
            print('- okay')

        self.db.sync()

    def run(self):
        for i, artid in enumerate(self.abstract_numbers):
            self.retrieve_article(artid)
            if (i + 1) % self.STATUS_PERIOD == 0:
                remaining = len(self.abstract_numbers) - (i + 1)
                print('=> {0} abstracts to go ({1} done)'.format(remaining, len(self.db)))

            time.sleep(random.choice(self.DELAY_DURATIONS))


if __name__ == '__main__':
    WasetAbstractRetriever('waset-abstracts.db').run()