def wait_and_add_to_queue(q_bulk_order):
"""Parse Id's from bulk-order queue(accepts requests from web) entry and add to mass-worker queue."""
log.write("%s Started wait_and_add_to_queue\n" % datetime.now())
log.flush()
while True:
info = json.loads(q_bulk_order.pop_and_remove())
ids = info[0]
email = info[1]
language = info[2]
ids = re.findall(r'[^,(\r\n)\s]+', ids)
no = len(ids)
q_mass_worker = get_shortest_queue()
library_id = 'gb'
redis_key3 = keys.redis_key3
redis = redis_py.Redis()
for book_id in ids:
book_id = gb.get_id_from_string(book_id)
book_key = "%s:%s:%s" % (redis_key3, library_id, book_id)
book_language_key = book_key + ":language"
redis_py.set(book_language_key, language, True)
q_mass_worker.add(book_id)
q_mass_worker.add(json.dumps((email, no)))
bulk_order_log.write("%s Received %s entries from %s\n" %
(datetime.now(), no, email))
bulk_order_log.flush()
def verify_id(Id_string):
"""Verify the Id and public-domain status for the book"""
Id = get_id_from_string(Id_string, 'desanitize')
if Id == None:
return 1
redis = redis_py.Redis()
redis_key3 = keys.redis_key3
book_key = "%s:%s:%s" %(redis_key3, 'usp', Id_string)
library_url_key = book_key + ":library_url"
url = redis_py.get(library_url_key, True)
url = get_absolute_url_of_book(url)
try:
r = requests.get(url)
except:
return 10
if r.status_code == 404:
return 1
if r.status_code != 200:
return 10
else:
source = r.text
soup = BeautifulSoup(source)
#public_domain = OAI_metadata_content("DC.relation", soup)
#if public_domain != "Domínio público".decode('utf-8') and public_domain != "":
#return 2
#else:
tld = extract_base_domain(url)
if tld[-1:] == '/':
tld = tld[:-1]
pdf_url = get_pdf_link(tld, soup)
if pdf_url == False:
return 8
return 0
def store_output_file_name(Id, output_file):
"""Save output file name to redis-memory"""
redis = redis_py.Redis()
redis_key3 = keys.redis_key3
book_key = redis_key3+":man:%s" %Id
output_file_key = book_key + ":output_file"
redis_py.set(output_file_key, output_file, True)
def verify_id(Id_string):
"""Verify the Id and public-domain status for the book"""
Id = get_id_from_string(Id_string, 'desanitize')
if Id == None:
return 1
redis = redis_py.Redis()
redis_key3 = keys.redis_key3
book_key = "%s:%s:%s" %(redis_key3, 'gal', Id_string)
library_url_key = book_key + ":library_url"
url = "http://gallica.bnf.fr/%s" %(Id)
try:
r = requests.get(url)
except:
return 10
if r.status_code == 404:
return 1
if r.status_code != 200:
return 10
else:
source = r.text
soup = BeautifulSoup(source)
rights= OAI_metadata_content("DC.rights", soup, burst=True)
for i in rights:
if not rights:
continue
if i.strip().lower().encode('utf-8') in ('domaine public', 'public domain'):
return 0
return 2
def check_if_upload_ready():
redis = redis_py.Redis()
redis_key2 = keys.redis_key2
lock_key1 = keys.lock_key1
q = redis_py.Queue(redis_key2)
Lock = redis_py.Lock(lock_key1)
while True:
book_keys = q.pop(-1)
if book_keys is False:
time.sleep(2)
continue
for book_key in book_keys:
uploaded = 0
ia_identifier = redis.get(book_key + ":ia_identifier")
ia_identifier = json.loads(ia_identifier)
if isinstance(ia_identifier, list):
Lock.acquire(timeout=60 * 2)
users_request = redis_py.smembers(book_key + ":requests", True)
if users_request != None:
redis.delete(book_key + ":requests")
remove_request_db(users_request, book_key)
remove_from_db(users_request)
Lock.release()
q.remove(book_key)
if users_request != None:
send_email(users_request, ia_identifier, book_key=book_key)
email_progress_key = book_key + ":email_progress"
redis_py.set(email_progress_key, 1, True)
delete_from_global_queue(book_key)
continue
else:
r = get_ia_metadata(ia_identifier)
if 'metadata' in r.keys():
if 'ocr' in r['metadata'].keys():
if r['metadata'][
'ocr'] == 'language not currently OCRable':
uploaded = 2
if 'DjVuTXT' in str(r) or 'Djvu XML' in str(r):
uploaded = 1
if uploaded != 0:
Lock.acquire(timeout=60 * 2)
users_request = redis_py.smembers(book_key + ":requests",
True)
if users_request != None:
redis.delete(book_key + ":requests")
remove_request_db(users_request, book_key)
remove_from_db(users_request)
Lock.release()
q.remove(book_key)
if users_request != None:
send_email(users_request, str(ia_identifier))
email_progress_key = book_key + ":email_progress"
redis_py.set(email_progress_key, 1, True)
delete_from_global_queue(book_key)
OCR_progress_key = book_key + ":OCR_progress"
redis_py.set(OCR_progress_key, 1, True)
else:
continue
time.sleep(2)
def __init__(self, value):
"""Assign variable"""
redis_key3 = keys.redis_key3
self.library = 'gb'
self.library_name = 'Google-Books'
self.Id = value.encode('utf-8')
self.ia_identifier = "bub_" + self.library + "_" + value
self.book_key = "%s:%s:%s" %(redis_key3, self.library, value)
self.redis = redis_py.Redis()
self.redis_output_file_key = "%s:%s:%s:output_file" %(redis_key3, self.library, self.Id)
def metadata(Id):
"""Return book information and meta-data"""
redis = redis_py.Redis()
redis_key3 = keys.redis_key3
book_key = "%s:%s:%s" %(redis_key3, 'usp', Id)
library_url_key = book_key + ":library_url"
url = redis_py.get(library_url_key, True)
url = get_absolute_url_of_book(url)
try:
r = requests.get(url)
except:
return 1
if r.status_code == 404:
return 1
if r.status_code != 200:
return 10
else:
source = r.text
if "Página não encontrada".decode('utf-8') in source:
return 1
soup = BeautifulSoup(source)
#public_domain = OAI_metadata_content("DC.relation", soup)
#if public_domain != "Domínio público".decode('utf-8') and public_domain != "":
#return 2
thumbnail_url = extract_thumbnail_url(soup, url)
return dict(
image_url = thumbnail_url,
thumbnail_url = thumbnail_url,
printType = "BOOK",
title = OAI_metadata_content("DC.title", soup),
subtitle = "",
author = OAI_metadata_content("DC.creator", soup),
publisher = OAI_metadata_content("DC.publisher", soup),
publishedDate = OAI_metadata_content("DCTERMS.issued", soup),
description = OAI_metadata_content("DC.description", soup),
infoLink = url,
publicDomain = True,
language = normalize_to_ascii(OAI_metadata_content("DC.language", soup)),
scanner = extract_base_domain(url),
sponser = extract_base_domain(url)
)
def metadata(Id):
"""Return book information and meta-data"""
redis = redis_py.Redis()
redis_key3 = keys.redis_key3
book_key = "%s:%s:%s" %(redis_key3, 'usp', Id)
Id_raw = get_id_from_string(Id, action = 'desanitize')
Id_raw = Id_raw[:-1] if Id_raw[-1] == '/' else Id_raw
library_url_key = book_key + ":library_url"
url = "http://gallica.bnf.fr/%s" %(Id_raw)
try:
r = requests.get(url)
except:
return 1
if r.status_code == 404:
return 1
if r.status_code != 200:
return 10
else:
source = r.text
soup = BeautifulSoup(source)
thumbnail_url = 'http://gallica.bnf.fr/%s.thumbnail' %Id_raw
source = r.text
soup = BeautifulSoup(source)
return dict(
image_url = thumbnail_url,
thumbnail_url = thumbnail_url,
printType = "BOOK",
title = OAI_metadata_content("DC.title", soup),
subtitle = "",
author = OAI_metadata_content("DC.creator", soup),
publisher = OAI_metadata_content("DC.publisher", soup),
publishedDate = OAI_metadata_content("DC.date", soup),
description = OAI_metadata_content("DC.description", soup),
infoLink = url,
publicDomain = True,
language = normalize_to_ascii(get_lang(source)),
scanner = "Gallica",
sponser = "Gallica"
)
def download_book(Id, id_for_key):
redis = redis_py.Redis()
redis_key3 = keys.redis_key3
book_key = "%s:%s:%s" %(redis_key3, 'usp', Id)
library_url_key = book_key + ":library_url"
url = redis_py.get(library_url_key, True)
url = get_absolute_url_of_book(url)
r = requests.get(url)
source = r.text
soup = BeautifulSoup(source)
tld = extract_base_domain(url)
if tld[-1:] == '/':
tld = tld[:-1]
pdf_url = get_pdf_link(tld, soup)
if pdf_url in ("", None):
return 1
pdf = requests.get(pdf_url, stream=True)
output_file = "/data/scratch/BUB_downloads/bub_usp_%s.pdf" %Id ###
store_output_file_name(id_for_key, output_file)
with open(output_file, 'wb') as f:
for chunk in pdf.iter_content(1024):
f.write(chunk)
return 0
def __init__(self, value):
"""Assign variable, and get metadata from cache"""
redis_key3 = keys.redis_key3
self.redis_key3 = redis_key3
self.redis = redis_py.Redis()
if isinstance(value, (int, long, float, complex)):
db = mysql_py.Db()
values = db.execute(
'select library, book_id from request where sno = %s;',
value)[0]
db.close()
self.library = values[0]
self.Id = values[1].encode('utf-8')
self.book_key = "%s:%s:%s" % (redis_key3, self.library, self.Id)
self.redis.set(redis_key3 + ":ongoing_job_identifier", self.Id)
self.ia_identifier = None
self.id_for_key = self.Id
else:
self.library = value['library']
self.Id = value['Id']
self.ia_identifier = "bub_" + self.library + "_" + value[
'ia_identifier_suffix']
self.book_key = "%s:%s:%s" % (redis_key3, self.library,
value['ia_identifier_suffix'])
self.redis.set(redis_key3 + ":ongoing_job_identifier",
value['ia_identifier_suffix'])
self.id_for_key = value['ia_identifier_suffix']
if '/' not in self.id_for_key:
self.redis_output_file_key = "%s:%s:%s:output_file" % (
redis_key3, self.library, self.id_for_key)
else:
self.redis_output_file_key = "%s:%s:%s:output_file" % (
redis_key3, self.library, hashlib.md5(
self.id_for_key).hexdigest())
self.library_name = bridge.lib_module(self.library)[1]
metadata_key = self.book_key + ":meta_data"
metadata = redis_py.get(metadata_key, True)
info = json.loads(metadata)
try:
self.title = info['title'].encode(
"utf-8") + " " + info['subtitle'].encode("utf-8")
except:
self.title = str(info['title'].encode("utf-8")) + " " + str(
info['subtitle'])
self.author = info['author'].encode("utf-8")
self.publisher = info['publisher'].encode("utf-8")
self.description = info['description'].replace("\n",
"").encode("utf-8")
self.printType = info['printType'].encode("utf-8")
self.publishedDate = re.sub("[^0123456789/.-]", "",
info['publishedDate'].encode("utf-8"))
self.infoLink = info['infoLink']
self.publicDomain = info['publicDomain']
language_code = info['language'].encode("utf-8")
if self.publishedDate not in (None, ""):
try:
self.publishedDate = re.sub('[x?]', '0', self.publishedDate)
self.year = parser.parse(self.publishedDate).year
self.month = parser.parse(self.publishedDate).month
self.day = parser.parse(self.publishedDate).day
except:
self.year = ""
self.month = ""
self.day = ""
else:
self.year = ""
self.month = ""
self.day = ""
try:
self.language = lang_code(language_code)
except:
self.language = ""
self.pdf_path = "/data/scratch/BUB_downloads/bub_%s_%s.pdf" % (
self.library, self.Id)
self.scanner = info['scanner']
self.sponser = info['sponser']
