gardenunez/arxiv_crawler.py

## arxiv_crawler.py
#!/usr/bin/env python
import urllib
import argparse
import sqlite3
from xml.dom import minidom
import datetime
from arxiv_subject_classification import SUBJECT_CLASSIFICATION


def get_args():
    """Get arguments"""
    parser = argparse.ArgumentParser(description="ArXiv crawler")
    parser.add_argument("-c", type=str, dest="cat",
                        help="Subject Classification or Category of Arxiv")


def create_db():
    print 'creating table'
    conn = sqlite3.connect('arxiv_crawler.db')
    c = conn.cursor()

    c.execute('''CREATE TABLE IF NOT EXISTS raw_data
                 (arxiv_id text, data text, created_date text)''')
    conn.commit()
    conn.close()

def select_top_ten_raw_data():
    print 'selecting crawled data'
    conn = sqlite3.connect('arxiv_crawler.db')
    c = conn.cursor()

    for row in c.execute('select * from raw_data limit 100'):
        print row
    conn.close()

def clean_raw_data():
    print 'cleaning raw data table'
    conn = sqlite3.connect('arxiv_crawler.db')
    c = conn.cursor()

    c.execute('delete from raw_data')
    conn.commit()
    conn.close()

def save_to_file(data, filename):
    with open(filename, 'w+') as arxiv_file:
        arxiv_file.write(data)
        print '{} file saved'.format(filename)


def save_arxiv_data_to_db(data):
    """Save arxiv xml raw data into arxiv_crawler db"""
    conn = sqlite3.connect('arxiv_crawler.db')
    try:
        c = conn.cursor()
        xmlobj = minidom.parseString(data)
        entries = xmlobj.getElementsByTagName('entry')
        raw_data_entries = []
        for entry in entries:
            url = entry.getElementsByTagName('id')[0].childNodes[0].data
            tokens = url.split('/')
            arxiv_id = tokens[len(tokens) - 1]
            raw_data_entries.append((arxiv_id, entry.toxml().replace('\n', ''), str(datetime.datetime.now())))
        c.executemany('INSERT INTO raw_data(arxiv_id, data, created_date) values (?,?,?)',
                      raw_data_entries)
        conn.commit()
    except Exception:
        conn.close()
        raise


def fetch_arxiv_data(category, offset=0, limit=100):
    url = 'http://export.arxiv.org/api/query?search_query=cat:{}&start={}&max_results={}'.format(
        category,
        offset,
        limit
    )
    data = urllib.urlopen(url).read()
    return data


def digest_arxiv_entry(xmlsource):
    """
    Parse an arxiv xml string
    :param xmlsource: str
    :return: list of articles
    """
    xmldata = minidom.parseString(xmlsource)
    articles = []
    entries = xmldata.getElementsByTagName('entry')
    for entry in entries:
        url = entry.getElementsByTagName('id')[0].childNodes[0].data
        doi_elem = entry.getElementsByTagName('arxiv:doi')
        doi = None
        if doi_elem:
            doi = doi_elem[0].childNodes[0].data
        title = entry.getElementsByTagName('title')[0].childNodes[0].data.encode('ascii', 'ignore').replace('\n', ' ')
        abstract = entry.getElementsByTagName('summary')[0].childNodes[0].data.encode('ascii', 'ignore').replace('\n', ' ').lstrip()
        published_date = entry.getElementsByTagName('published')[0].childNodes[0].data
        updated_date = entry.getElementsByTagName('updated')[0].childNodes[0].data
        articles.append(
            {
                'doi': doi,
                'title': title,
                'abstract': abstract,
                'published': published_date,
                'updated': updated_date,
                'url': url
            }
        )
    return articles

def crawl_all_categories():
    """Crawl all entries from all categories"""
    print 'start crawling all categories'
    #TODO uncomment this
    # for cat in SUBJECT_CLASSIFICATION.keys():
    for cat in SUBJECT_CLASSIFICATION.keys()[:5]:
        crawl_by_category(cat)
    print 'end process!!'

def crawl_by_category(cat):
    if cat not in SUBJECT_CLASSIFICATION:
        raise Exception("Invalid category")
    cat_name = SUBJECT_CLASSIFICATION[cat]
    print 'crawling category: {}'.format(cat_name)
    data = fetch_arxiv_data(cat, 0, 1)
    xml_data = minidom.parseString(data)
    # TODO uncomment this
    # total_results = int(xml_data.getElementsByTagName('opensearch:totalResults')[0].childNodes[0].data)
    total_results = 5
    print 'starting to fetch {} entries'.format(total_results)
    if total_results > 0:
        offset = -10
        limit = 10
        while offset < total_results:
            offset += limit
            data = fetch_arxiv_data(cat, offset, limit)
            save_arxiv_data_to_db(data)
            #filename = "arxiv_{}_{}_{}.xml".format(cat, offset, limit)
            #saveToFile(data, filename)
    print 'end crawling {}!!'.format(cat_name)


def main():
    create_db()
    clean_raw_data()
    crawl_all_categories()
    select_top_ten_raw_data()

if __name__ == '__main__':
    main()

## arxiv_subject_classification.py
#!/usr/bin/env python

SUBJECT_CLASSIFICATION = {
"stat.AP":	"Statistics - Applications",
"stat.CO":	"Statistics - Computation",
"stat.ML":	"Statistics - Machine Learning",
"stat.ME":	"Statistics - Methodology",
"stat.TH":	"Statistics - Theory",
"q-bio.BM": "Quantitative Biology - Biomolecules",
"q-bio.CB": "Quantitative Biology - Cell Behavior",
"q-bio.GN": "Quantitative Biology - Genomics",
"q-bio.MN": "Quantitative Biology - Molecular Networks",
"q-bio.NC": "Quantitative Biology - Neurons and Cognition",
"q-bio.OT": "Quantitative Biology - Other",
"q-bio.PE": "Quantitative Biology - Populations and Evolution",
"q-bio.QM": "Quantitative Biology - Quantitative Methods",
"q-bio.SC": "Quantitative Biology - Subcellular Processes",
"q-bio.TO": "Quantitative Biology - Tissues and Organs",
"cs.AR": "Computer Science - Architecture",
"cs.AI":"Computer Science - Artificial Intelligence",
"cs.CL":"Computer Science - Computation and Language",
"cs.CC":"Computer Science - Computational Complexity",
"cs.CE":"Computer Science - Computational Engineering; Finance; and Science",
"cs.CG":"Computer Science - Computational Geometry",
"cs.GT":"Computer Science - Computer Science and Game Theory",
"cs.CV":"Computer Science - Computer Vision and Pattern Recognition",
"cs.CY":"Computer Science - Computers and Society",
"cs.CR":"Computer Science - Cryptography and Security",
"cs.DS":"Computer Science - Data Structures and Algorithms",
"cs.DB":"Computer Science - Databases",
"cs.DL":"Computer Science - Digital Libraries",
"cs.DM":"Computer Science - Discrete Mathematics",
"cs.DC":"Computer Science - Distributed; Parallel; and Cluster Computing",
"cs.GL":"Computer Science - General Literature",
"cs.GR":"Computer Science - Graphics",
"cs.HC":"Computer Science - Human-Computer Interaction",
"cs.IR":"Computer Science - Information Retrieval",
"cs.IT":"Computer Science - Information Theory",
"cs.LG":"Computer Science - Learning",
"cs.LO":"Computer Science - Logic in Computer Science",
"cs.MS":"Computer Science - Mathematical Software",
"cs.MA":"Computer Science - Multiagent Systems",
"cs.MM":"Computer Science - Multimedia",
"cs.NI":"Computer Science - Networking and Internet Architecture",
"cs.NE":"Computer Science - Neural and Evolutionary Computing",
"cs.NA":"Computer Science - Numerical Analysis",
"cs.OS":"Computer Science - Operating Systems",
"cs.OH":"Computer Science - Other",
"cs.PF":"Computer Science - Performance",
"cs.PL":"Computer Science - Programming Languages",
"cs.RO":"Computer Science - Robotics",
"cs.SE":"Computer Science - Software Engineering",
"cs.SD":"Computer Science - Sound",
"cs.SC":"Computer Science - Symbolic Computation",
"nlin.AO": "Nonlinear Sciences - Adaptation and Self-Organizing Systems",
"nlin.CG": "Nonlinear Sciences - Cellular Automata and Lattice Gases",
"nlin.CD": "Nonlinear Sciences - Chaotic Dynamics",
"nlin.SI": "Nonlinear Sciences - Exactly Solvable and Integrable Systems",
"nlin.PS": "Nonlinear Sciences - Pattern Formation and Solitons",
"math.AG": "Mathematics - Algebraic Geometry",
"math.AT": "Mathematics - Algebraic Topology",
"math.AP": "Mathematics - Analysis of PDEs",
"math.CT": "Mathematics - Category Theory",
"math.CA": "Mathematics - Classical Analysis and ODEs",
"math.CO": "Mathematics - Combinatorics",
"math.AC": "Mathematics - Commutative Algebra",
"math.CV": "Mathematics - Complex Variables",
"math.DG": "Mathematics - Differential Geometry",
"math.DS": "Mathematics - Dynamical Systems",
"math.FA": "Mathematics - Functional Analysis",
"math.GM": "Mathematics - General Mathematics",
"math.GN": "Mathematics - General Topology",
"math.GT": "Mathematics - Geometric Topology",
"math.GR": "Mathematics - Group Theory",
"math.HO": "Mathematics - History and Overview",
"math.IT": "Mathematics - Information Theory",
"math.KT": "Mathematics - K-Theory and Homology",
"math.LO": "Mathematics - Logic",
"math.MP": "Mathematics - Mathematical Physics",
"math.MG": "Mathematics - Metric Geometry",
"math.NT": "Mathematics - Number Theory",
"math.NA": "Mathematics - Numerical Analysis",
"math.OA": "Mathematics - Operator Algebras",
"math.OC": "Mathematics - Optimization and Control",
"math.PR": "Mathematics - Probability",
"math.QA": "Mathematics - Quantum Algebra",
"math.RT": "Mathematics - Representation Theory",
"math.RA": "Mathematics - Rings and Algebras",
"math.SP": "Mathematics - Spectral Theory",
"math.ST": "Mathematics - Statistics",
"math.SG": "Mathematics - Symplectic Geometry",
"astro-ph": "Astrophysics",
"cond-mat.dis-nn": "Physics - Disordered Systems and Neural Networks",
"cond-mat.mes-hall": "Physics - Mesoscopic Systems and Quantum Hall Effect",
"cond-mat.mtrl-sci": "Physics - Materials Science",
"cond-mat.other": "Physics - Other",
"cond-mat.soft": "Physics - Soft Condensed Matter",
"cond-mat.stat-mech": "Physics - Statistical Mechanics",
"cond-mat.str-el": "Physics - Strongly Correlated Electrons",
"cond-mat.supr-con": "Physics - Superconductivity",
"gr-qc": "General Relativity and Quantum Cosmology",
"hep-ex": "High Energy Physics - Experiment",
"hep-lat": "High Energy Physics - Lattice",
"hep-ph": "High Energy Physics - Phenomenology",
"hep-th": "High Energy Physics - Theory",
"math-ph": "Mathematical Physics",
"nucl-ex": "Nuclear Experiment",
"nucl-th":" Nuclear Theory",
"physics.acc-ph": "Physics - Accelerator Physics",
"physics.ao-ph": "Physics - Atmospheric and Oceanic Physics",
"physics.atom-ph": "Physics - Atomic Physics",
"physics.atm-clus": "Physics - Atomic and Molecular Clusters",
"physics.bio-ph": "Physics - Biological Physics",
"physics.chem-ph": "Physics - Chemical Physics",
"physics.class-ph": "Physics - Classical Physics",
"physics.comp-ph": "Physics - Computational Physics",
"physics.data-an": "Physics - Data Analysis; Statistics and Probability",
"physics.flu-dyn": "Physics - Fluid Dynamics",
"physics.gen-ph": "Physics - General Physics",
"physics.geo-ph": "Physics - Geophysics",
"physics.hist-ph": "Physics - History of Physics",
"physics.ins-det": "Physics - Instrumentation and Detectors",
"physics.med-ph": "Physics - Medical Physics",
"physics.optics": "Physics - Optics",
"physics.ed-ph": "Physics - Physics Education",
"physics.soc-ph": "Physics - Physics and Society",
"physics.plasm-ph": "Physics - Plasma Physics",
"physics.pop-ph": "Physics - Popular Physics",
"physics.space-ph":	"Physics - Space Physics",
"quant-ph":	"Quantum Physics"
}
	#!/usr/bin/env python
	import urllib
	import argparse
	import sqlite3
	from xml.dom import minidom
	import datetime
	from arxiv_subject_classification import SUBJECT_CLASSIFICATION


	def get_args():
	"""Get arguments"""
	parser = argparse.ArgumentParser(description="ArXiv crawler")
	parser.add_argument("-c", type=str, dest="cat",
	help="Subject Classification or Category of Arxiv")


	def create_db():
	print 'creating table'
	conn = sqlite3.connect('arxiv_crawler.db')
	c = conn.cursor()

	c.execute('''CREATE TABLE IF NOT EXISTS raw_data
	(arxiv_id text, data text, created_date text)''')
	conn.commit()
	conn.close()

	def select_top_ten_raw_data():
	print 'selecting crawled data'
	conn = sqlite3.connect('arxiv_crawler.db')
	c = conn.cursor()

	for row in c.execute('select * from raw_data limit 100'):
	print row
	conn.close()

	def clean_raw_data():
	print 'cleaning raw data table'
	conn = sqlite3.connect('arxiv_crawler.db')
	c = conn.cursor()

	c.execute('delete from raw_data')
	conn.commit()
	conn.close()

	def save_to_file(data, filename):
	with open(filename, 'w+') as arxiv_file:
	arxiv_file.write(data)
	print '{} file saved'.format(filename)


	def save_arxiv_data_to_db(data):
	"""Save arxiv xml raw data into arxiv_crawler db"""
	conn = sqlite3.connect('arxiv_crawler.db')
	try:
	c = conn.cursor()
	xmlobj = minidom.parseString(data)
	entries = xmlobj.getElementsByTagName('entry')
	raw_data_entries = []
	for entry in entries:
	url = entry.getElementsByTagName('id')[0].childNodes[0].data
	tokens = url.split('/')
	arxiv_id = tokens[len(tokens) - 1]
	raw_data_entries.append((arxiv_id, entry.toxml().replace('\n', ''), str(datetime.datetime.now())))
	c.executemany('INSERT INTO raw_data(arxiv_id, data, created_date) values (?,?,?)',
	raw_data_entries)
	conn.commit()
	except Exception:
	conn.close()
	raise


	def fetch_arxiv_data(category, offset=0, limit=100):
	url = 'http://export.arxiv.org/api/query?search_query=cat:{}&start={}&max_results={}'.format(
	category,
	offset,
	limit
	)
	data = urllib.urlopen(url).read()
	return data


	def digest_arxiv_entry(xmlsource):
	"""
	Parse an arxiv xml string
	:param xmlsource: str
	:return: list of articles
	"""
	xmldata = minidom.parseString(xmlsource)
	articles = []
	entries = xmldata.getElementsByTagName('entry')
	for entry in entries:
	url = entry.getElementsByTagName('id')[0].childNodes[0].data
	doi_elem = entry.getElementsByTagName('arxiv:doi')
	doi = None
	if doi_elem:
	doi = doi_elem[0].childNodes[0].data
	title = entry.getElementsByTagName('title')[0].childNodes[0].data.encode('ascii', 'ignore').replace('\n', ' ')
	abstract = entry.getElementsByTagName('summary')[0].childNodes[0].data.encode('ascii', 'ignore').replace('\n', ' ').lstrip()
	published_date = entry.getElementsByTagName('published')[0].childNodes[0].data
	updated_date = entry.getElementsByTagName('updated')[0].childNodes[0].data
	articles.append(
	{
	'doi': doi,
	'title': title,
	'abstract': abstract,
	'published': published_date,
	'updated': updated_date,
	'url': url
	}
	)
	return articles

	def crawl_all_categories():
	"""Crawl all entries from all categories"""
	print 'start crawling all categories'
	#TODO uncomment this
	# for cat in SUBJECT_CLASSIFICATION.keys():
	for cat in SUBJECT_CLASSIFICATION.keys()[:5]:
	crawl_by_category(cat)
	print 'end process!!'

	def crawl_by_category(cat):
	if cat not in SUBJECT_CLASSIFICATION:
	raise Exception("Invalid category")
	cat_name = SUBJECT_CLASSIFICATION[cat]
	print 'crawling category: {}'.format(cat_name)
	data = fetch_arxiv_data(cat, 0, 1)
	xml_data = minidom.parseString(data)
	# TODO uncomment this
	# total_results = int(xml_data.getElementsByTagName('opensearch:totalResults')[0].childNodes[0].data)
	total_results = 5
	print 'starting to fetch {} entries'.format(total_results)
	if total_results > 0:
	offset = -10
	limit = 10
	while offset < total_results:
	offset += limit
	data = fetch_arxiv_data(cat, offset, limit)
	save_arxiv_data_to_db(data)
	#filename = "arxiv_{}_{}_{}.xml".format(cat, offset, limit)
	#saveToFile(data, filename)
	print 'end crawling {}!!'.format(cat_name)


	def main():
	create_db()
	clean_raw_data()
	crawl_all_categories()
	select_top_ten_raw_data()

	if __name__ == '__main__':
	main()
	#!/usr/bin/env python

	SUBJECT_CLASSIFICATION = {
	"stat.AP": "Statistics - Applications",
	"stat.CO": "Statistics - Computation",
	"stat.ML": "Statistics - Machine Learning",
	"stat.ME": "Statistics - Methodology",
	"stat.TH": "Statistics - Theory",
	"q-bio.BM": "Quantitative Biology - Biomolecules",
	"q-bio.CB": "Quantitative Biology - Cell Behavior",
	"q-bio.GN": "Quantitative Biology - Genomics",
	"q-bio.MN": "Quantitative Biology - Molecular Networks",
	"q-bio.NC": "Quantitative Biology - Neurons and Cognition",
	"q-bio.OT": "Quantitative Biology - Other",
	"q-bio.PE": "Quantitative Biology - Populations and Evolution",
	"q-bio.QM": "Quantitative Biology - Quantitative Methods",
	"q-bio.SC": "Quantitative Biology - Subcellular Processes",
	"q-bio.TO": "Quantitative Biology - Tissues and Organs",
	"cs.AR": "Computer Science - Architecture",
	"cs.AI":"Computer Science - Artificial Intelligence",
	"cs.CL":"Computer Science - Computation and Language",
	"cs.CC":"Computer Science - Computational Complexity",
	"cs.CE":"Computer Science - Computational Engineering; Finance; and Science",
	"cs.CG":"Computer Science - Computational Geometry",
	"cs.GT":"Computer Science - Computer Science and Game Theory",
	"cs.CV":"Computer Science - Computer Vision and Pattern Recognition",
	"cs.CY":"Computer Science - Computers and Society",
	"cs.CR":"Computer Science - Cryptography and Security",
	"cs.DS":"Computer Science - Data Structures and Algorithms",
	"cs.DB":"Computer Science - Databases",
	"cs.DL":"Computer Science - Digital Libraries",
	"cs.DM":"Computer Science - Discrete Mathematics",
	"cs.DC":"Computer Science - Distributed; Parallel; and Cluster Computing",
	"cs.GL":"Computer Science - General Literature",
	"cs.GR":"Computer Science - Graphics",
	"cs.HC":"Computer Science - Human-Computer Interaction",
	"cs.IR":"Computer Science - Information Retrieval",
	"cs.IT":"Computer Science - Information Theory",
	"cs.LG":"Computer Science - Learning",
	"cs.LO":"Computer Science - Logic in Computer Science",
	"cs.MS":"Computer Science - Mathematical Software",
	"cs.MA":"Computer Science - Multiagent Systems",
	"cs.MM":"Computer Science - Multimedia",
	"cs.NI":"Computer Science - Networking and Internet Architecture",
	"cs.NE":"Computer Science - Neural and Evolutionary Computing",
	"cs.NA":"Computer Science - Numerical Analysis",
	"cs.OS":"Computer Science - Operating Systems",
	"cs.OH":"Computer Science - Other",
	"cs.PF":"Computer Science - Performance",
	"cs.PL":"Computer Science - Programming Languages",
	"cs.RO":"Computer Science - Robotics",
	"cs.SE":"Computer Science - Software Engineering",
	"cs.SD":"Computer Science - Sound",
	"cs.SC":"Computer Science - Symbolic Computation",
	"nlin.AO": "Nonlinear Sciences - Adaptation and Self-Organizing Systems",
	"nlin.CG": "Nonlinear Sciences - Cellular Automata and Lattice Gases",
	"nlin.CD": "Nonlinear Sciences - Chaotic Dynamics",
	"nlin.SI": "Nonlinear Sciences - Exactly Solvable and Integrable Systems",
	"nlin.PS": "Nonlinear Sciences - Pattern Formation and Solitons",
	"math.AG": "Mathematics - Algebraic Geometry",
	"math.AT": "Mathematics - Algebraic Topology",
	"math.AP": "Mathematics - Analysis of PDEs",
	"math.CT": "Mathematics - Category Theory",
	"math.CA": "Mathematics - Classical Analysis and ODEs",
	"math.CO": "Mathematics - Combinatorics",
	"math.AC": "Mathematics - Commutative Algebra",
	"math.CV": "Mathematics - Complex Variables",
	"math.DG": "Mathematics - Differential Geometry",
	"math.DS": "Mathematics - Dynamical Systems",
	"math.FA": "Mathematics - Functional Analysis",
	"math.GM": "Mathematics - General Mathematics",
	"math.GN": "Mathematics - General Topology",
	"math.GT": "Mathematics - Geometric Topology",
	"math.GR": "Mathematics - Group Theory",
	"math.HO": "Mathematics - History and Overview",
	"math.IT": "Mathematics - Information Theory",
	"math.KT": "Mathematics - K-Theory and Homology",
	"math.LO": "Mathematics - Logic",
	"math.MP": "Mathematics - Mathematical Physics",
	"math.MG": "Mathematics - Metric Geometry",
	"math.NT": "Mathematics - Number Theory",
	"math.NA": "Mathematics - Numerical Analysis",
	"math.OA": "Mathematics - Operator Algebras",
	"math.OC": "Mathematics - Optimization and Control",
	"math.PR": "Mathematics - Probability",
	"math.QA": "Mathematics - Quantum Algebra",
	"math.RT": "Mathematics - Representation Theory",
	"math.RA": "Mathematics - Rings and Algebras",
	"math.SP": "Mathematics - Spectral Theory",
	"math.ST": "Mathematics - Statistics",
	"math.SG": "Mathematics - Symplectic Geometry",
	"astro-ph": "Astrophysics",
	"cond-mat.dis-nn": "Physics - Disordered Systems and Neural Networks",
	"cond-mat.mes-hall": "Physics - Mesoscopic Systems and Quantum Hall Effect",
	"cond-mat.mtrl-sci": "Physics - Materials Science",
	"cond-mat.other": "Physics - Other",
	"cond-mat.soft": "Physics - Soft Condensed Matter",
	"cond-mat.stat-mech": "Physics - Statistical Mechanics",
	"cond-mat.str-el": "Physics - Strongly Correlated Electrons",
	"cond-mat.supr-con": "Physics - Superconductivity",
	"gr-qc": "General Relativity and Quantum Cosmology",
	"hep-ex": "High Energy Physics - Experiment",
	"hep-lat": "High Energy Physics - Lattice",
	"hep-ph": "High Energy Physics - Phenomenology",
	"hep-th": "High Energy Physics - Theory",
	"math-ph": "Mathematical Physics",
	"nucl-ex": "Nuclear Experiment",
	"nucl-th":" Nuclear Theory",
	"physics.acc-ph": "Physics - Accelerator Physics",
	"physics.ao-ph": "Physics - Atmospheric and Oceanic Physics",
	"physics.atom-ph": "Physics - Atomic Physics",
	"physics.atm-clus": "Physics - Atomic and Molecular Clusters",
	"physics.bio-ph": "Physics - Biological Physics",
	"physics.chem-ph": "Physics - Chemical Physics",
	"physics.class-ph": "Physics - Classical Physics",
	"physics.comp-ph": "Physics - Computational Physics",
	"physics.data-an": "Physics - Data Analysis; Statistics and Probability",
	"physics.flu-dyn": "Physics - Fluid Dynamics",
	"physics.gen-ph": "Physics - General Physics",
	"physics.geo-ph": "Physics - Geophysics",
	"physics.hist-ph": "Physics - History of Physics",
	"physics.ins-det": "Physics - Instrumentation and Detectors",
	"physics.med-ph": "Physics - Medical Physics",
	"physics.optics": "Physics - Optics",
	"physics.ed-ph": "Physics - Physics Education",
	"physics.soc-ph": "Physics - Physics and Society",
	"physics.plasm-ph": "Physics - Plasma Physics",
	"physics.pop-ph": "Physics - Popular Physics",
	"physics.space-ph": "Physics - Space Physics",
	"quant-ph": "Quantum Physics"
	}