def main():
global _zip_main
modulename = _zip_main if _zip_main[-4:] != '-dev' else _zip_main[:-4]
sys.FG_RELOAD = True
while sys.FG_RELOAD:
sys.FG_RELOAD = False
m = sys.reload(modulename)
if hasattr(m, 'init'):
m.init()
m.main()
import requests
import datetime
import re
import time
import random
import sys
try:
from urllib import parse as parse
except:
import urllib as parse
sys.reload()
sys.setdefaultencoding('utf-8')
def init_cookies():
"""
return the cookies after your first visit
"""
headers = {
'Upgrade-Insecure-Requests': '1',
'Host': 'm.lagou.com',
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'User-Agent':
'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1',
'DNT': '1',
'Cache-Control': 'max-age=0',
'Referrer Policy': 'no-referrer-when-downgrade',
#-*- encoding:utf-8 -*-
from __future__ import (absolute_import, division, print_function,
unicode_literals)
import sys
try:
sys.reload(sys)
sys.setdefaultencoding('utf-8')
except:
pass
import mlstudiosdk.modules
import mlstudiosdk.solution_gallery
from mlstudiosdk.modules.components.component import LComponent
from mlstudiosdk.modules.components.settings import Setting
from mlstudiosdk.modules.components.utils.orange_table_2_data_frame import table2df
from mlstudiosdk.modules.algo.data import Domain, Table
from mlstudiosdk.modules.algo.evaluation import Results
from mlstudiosdk.modules.algo.data.variable import DiscreteVariable, ContinuousVariable
from mlstudiosdk.modules.utils.itemlist import MetricFrame
import warnings
import jieba.posseg as pseg
import codecs
import os
import re
import util #modify the code for test
#import mlstudiosdk.modules.components.nlp.Text_Extract_Keywords_Util as util
warnings.filterwarnings('ignore')
import requests
from requests import Session
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), os.pardir)))
from util.excel_helper import mkdirs_if_not_exists
from util.file_reader import parse_job_xml
from util import log
try:
from urllib import parse as parse
except:
import urllib as parse
sys.reload()
sys.setdefaultencoding('utf-8')
def init_cookies():
"""
return the cookies after your first visit
"""
headers = {
'Upgrade-Insecure-Requests': '1',
'Host': 'm.lagou.com',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1',
'DNT': '1',
'Cache-Control': 'max-age=0',
'Referrer Policy': 'no-referrer-when-downgrade',
Simple harvester for Dutch last names.
Data-source:
http://www.meertens.knaw.nl/nfb/
:copyright: (c) 2016 Koninklijke Bibliotheek, by Willem-Jan Faber.
:license: GPLv3
https://github.com/KBNLresearch/Narralyzer/blob/master/licence.txt
"""
import lxml.html
import sys
import urllib.request
sys.reload(sys)
sys.setdefaultencoding('utf-8')
BASEURL = "http://www.meertens.knaw.nl/nfb/lijst_namen.php?operator=cn&naam=%s"
DEBUG = False
vowels = ['a',
'e',
'i',
'o',
'u']
forbidden = ['Naam',
'Centraal Bureau voor Genealogie',
'KNAW/Meertens Instituut']