Python 数组按单词过滤

Question

我在编程方面很弱。我需要根据以下逻辑过滤数据数组，但我不明白该怎么做。使用 "while" 循环，但我认为这将花费很多时间，因为数组非常大。

我有非常大的打印机阵列驱动程序：

[...
{"PPD_NAME": "HP PSC 2500 Series, hpcups 3.18.5 (en)", "PPD_PATH": "hplip:4/ppd/hplip/HP/hp-psc_2500_series.ppd"}, 
{"PPD_NAME": "HP LaserJet m3035 MFP hpijs pcl3, 3.18.5 (en)", "PPD_PATH": "drv:///hpijs.drv/hp-laserjet_m3035_mfp-pcl3-hpijs.ppd"}, 
{"PPD_NAME": "HP LaserJet m2727 MFP pcl3, hpcups 3.18.5 (en)", "PPD_PATH": "drv:///hpcups.drv/hp-laserjet_m2727_mfp-pcl3.ppd"}
...]

并有字符串(名称打印机(：

"HP HP LaserJet m2727 Multifunction Printer"

我想按单词拆分字符串并按每个单词过滤数组，直到出现"无"。

例：

循环 1： 字："HP"结果：

{"PPD_NAME": "HP PSC 2500 Series, hpcups 3.18.5 (en)", "PPD_PATH": "hplip:4/ppd/hplip/HP/hp-psc_2500_series.ppd"}, {"PPD_NAME": "HP LaserJet m3035 MFP hpijs pcl3, 3.18.5 (en)", "PPD_PATH": "drv:///hpijs.drv/hp-laserjet_m3035_mfp-pcl3-hpijs.ppd"}, {"PPD_NAME": "HP LaserJet m2727 MFP pcl3, hpcups 3.18.5 (en)", "PPD_PATH": "drv:///hpcups.drv/hp-laserjet_m2727_mfp-pcl3.ppd"}

循环 2： 字："LaserJet"结果：

{"PPD_NAME": "HP LaserJet m3035 MFP hpijs pcl3, 3.18.5 (en)", "PPD_PATH": "drv:///hpijs.drv/hp-laserjet_m3035_mfp-pcl3-hpijs.ppd"}, {"PPD_NAME": "HP LaserJet m2727 MFP pcl3, hpcups 3.18.5 (en)", "PPD_PATH": "drv:///hpcups.drv/hp-laserjet_m2727_mfp-pcl3.ppd"}

循环 3： 字："m2727"

结果：

{"PPD_NAME": "HP LaserJet m2727 MFP pcl3, hpcups 3.18.5 (en)", "PPD_PATH": "drv:///hpcups.drv/hp-laserjet_m2727_mfp-pcl3.ppd"}

循环 4： 字："Multifunction"

结果：None我想得到最后一个迭代的第一个对象，而不是"无"：{"PPD_NAME": "HP LaserJet m2727 MFP pcl3, hpcups 3.18.5 (en)",{...}}

前提是结果为"无"或单词已完成。 如何在 python 上制作类似的过滤器？ 有人这些？

for word in ArgInListFindNewPrinters['PRINTER_INFO'].split():
name = next(name for name in ListPrinterDriver if re.search(word, str(name), re.IGNORECASE))
print name

但它没有像我预期的那样工作。

编辑：我的结果较低。此脚本在 CUPS(可用打印机(中搜索打印机并添加它。如果可以以某种方式对其进行优化，我将不胜感激。

#!/usr/bin/python
# -*- coding: UTF-8 -*-
import requests
import json
import sys
from bs4 import BeautifulSoup
import re
def GetFindNewPrinters(cookie):
headers = {}
headers["Cookie"] = 'org.cups.sid='+cookie["org.cups.sid"]
FromData = {}
FromData["OP"] = 'find-new-printers'
FromData["org.cups.sid"] = cookie["org.cups.sid"]
Responce = requests.post(url, headers=headers, data=FromData)
soup = BeautifulSoup(Responce.content.decode('utf-8'), 'html.parser')
ListFindNewPrinters = []
for id, link in enumerate(soup.find_all('form')):
ListFindNewPrinters.append({'TEMPLATE_NAME': link.find("input", {"name":"TEMPLATE_NAME"})['value']})
ListFindNewPrinters[id]['DEVICE_URI'] = link.find("input", {"name":"DEVICE_URI"})['value']
ListFindNewPrinters[id]['PRINTER_LOCATION'] = link.find("input", {"name":"PRINTER_LOCATION"})['value']
ListFindNewPrinters[id]['PRINTER_INFO'] = link.find("input", {"name":"PRINTER_INFO"})['value']
return ListFindNewPrinters
def GetPrinterDrivers(cookie,PRINTER_NAME,PRINTER_INFO,PRINTER_LOCATION,DEVICE_URI):
headers = {}
headers["Cookie"] = 'org.cups.sid='+cookie["org.cups.sid"]
FromData = {}
FromData["OP"] = 'add-printer'
FromData["org.cups.sid"] = cookie["org.cups.sid"]
FromData["PRINTER_IS_SHARED"] = 'on'
FromData["PRINTER_LOCATION"] = PRINTER_LOCATION
FromData["PRINTER_INFO"] = PRINTER_INFO
FromData["PRINTER_NAME"] = PRINTER_NAME
FromData["DEVICE_URI"] = DEVICE_URI
FromData["PPD_MAKE"] = PRINTER_INFO.split(' ', 1)[0]
FromData["PPD_FILE"] = '(binary)'
Responce = requests.post(url, headers=headers, data=FromData)
soup = BeautifulSoup(Responce.content.decode('utf-8'), 'html.parser')
ListPrinterDriver = []
for id, link in enumerate(soup.find_all('option')):
ListPrinterDriver.append({'PPD_PATH': link['value']})
ListPrinterDriver[id]['PPD_NAME'] = link.next.replace("n","")
return ListPrinterDriver
def FindInArrayByWord(ArrayDrivers,PrinterName):
if ArrayDrivers == []:
return None
for word in PrinterName.split():
if FindInArray(ArrayDrivers,word) == []:
break
else:
ArrayDrivers = FindInArray(ArrayDrivers,word)
return ArrayDrivers[0]
def AddPrinter(cookie,PRINTER_NAME,PRINTER_INFO,PRINTER_LOCATION,DEVICE_URI,PPD_NAME):
headers = {}
headers["Cookie"] = 'org.cups.sid='+cookie["org.cups.sid"]
FromData = {}
FromData["org.cups.sid"] = cookie["org.cups.sid"]
FromData["OP"] = 'add-printer'
FromData["printer_name"] = PRINTER_NAME
FromData["PRINTER_NAME"] = PRINTER_NAME
FromData["PRINTER_INFO"] = PRINTER_INFO
FromData["PRINTER_LOCATION"] = PRINTER_LOCATION
FromData["DEVICE_URI"] = DEVICE_URI
FromData["PRINTER_IS_SHARED"] = 'on'
FromData["PPD_NAME"] = PPD_NAME
FromData["MAX_FILE_SIZE"] = '262144'
FromData["PPD_FILE"] = '(binary)'
Responce = requests.post(url, headers=headers, data=FromData)
return Responce
def AddPrinterOptions(cookie,PRINTER_NAME):
headers = {}
headers["Cookie"] = 'org.cups.sid='+cookie["org.cups.sid"]
FromData = {}
FromData["org.cups.sid"] = cookie["org.cups.sid"]
FromData["PRINTER_NAME"] = PRINTER_NAME
FromData["OP"] = 'set-printer-options'
FromData["PageSize"] = 'A4'
FromData["PageSize.Width"] = '0'
FromData["PageSize.Height"] = '0'
FromData["PageSize.Units"] = 'pt'
FromData["Duplex"] = 'None'
FromData["job_sheets_start"] = 'none'
FromData["job_sheets_end"] = 'none'
FromData["printer_error_policy"] = 'retry-job'
FromData["printer_op_policy"] = 'default'
Responce = requests.post(url, headers=headers, data=FromData)
return Responce
def FindInArray(Array,Arg,*args):
ArrayObject = None
NewArray = []
if len(args) != 0:
for ArrayObjectName in args:
try:
ArrayObject = [name for name in Array if re.search(Arg, name[ArrayObjectName], re.IGNORECASE)]
except StopIteration: pass
else:
try:
ArrayObject = [name for name in Array if re.search(Arg, str(name), re.IGNORECASE)]
except StopIteration: pass
return ArrayObject

def main():
# Check connection
try:
Responce = requests.get(url, timeout=10)
except requests.exceptions.RequestException as e:
print e
sys.exit(-1)
# Get list available printers in CUPS, and find. Else add printer with specific destination.
if sys.argv[3] != 'False':
ArgPrinterIP = sys.argv[3]
ArgInListFindNewPrinters = {}
ArgInListFindNewPrinters["TEMPLATE_NAME"] = ArgPrinter.replace(" ", "_")
ArgInListFindNewPrinters["PRINTER_INFO"] = ArgPrinter
ArgInListFindNewPrinters["PRINTER_LOCATION"] = 'Добавленный по IP'
ArgInListFindNewPrinters["DEVICE_URI"] = 'socket://'+ArgPrinterIP
else:
ListFindNewPrinters = GetFindNewPrinters(Responce.cookies)
ArgInListFindNewPrinters = FindInArrayByWord(ListFindNewPrinters,ArgPrinter)
if ArgInListFindNewPrinters == None:
print "Not find printers with arguments."
sys.exit(1)
ListPrinterDriver = GetPrinterDrivers(Responce.cookies,ArgInListFindNewPrinters['TEMPLATE_NAME'],ArgInListFindNewPrinters['PRINTER_INFO'],ArgInListFindNewPrinters['PRINTER_LOCATION'],ArgInListFindNewPrinters['DEVICE_URI'])
Driver = FindInArrayByWord(ListPrinterDriver,ArgInListFindNewPrinters['PRINTER_INFO'])
AddPrinter(Responce.cookies,ArgInListFindNewPrinters['TEMPLATE_NAME'],ArgInListFindNewPrinters['PRINTER_INFO'],ArgInListFindNewPrinters['PRINTER_LOCATION'],ArgInListFindNewPrinters['DEVICE_URI'],Driver['PPD_PATH'])
AddPrinterOptions(Responce.cookies,ArgInListFindNewPrinters['TEMPLATE_NAME'])
print "Printer: "+ArgInListFindNewPrinters['TEMPLATE_NAME']+". Succesfull add."
# Set arguments
ArgURL = sys.argv[1]
ArgPrinter = sys.argv[2]
url = 'http://'+ArgURL+':631/admin/'
if __name__ == "__main__":
try:
main()
except Exception as e:
print e
sys.exit(0)

Answer 1

使用正则表达式与所需的筛选器匹配。

import re
# List of printers
printers = [{"PPD_NAME": "HP PSC 2500 Series, hpcups 3.18.5 (en)", "PPD_PATH": "hplip:4/ppd/hplip/HP/hp-psc_2500_series.ppd"}, 
{"PPD_NAME": "HP LaserJet m3035 MFP hpijs pcl3, 3.18.5 (en)", "PPD_PATH": "drv:///hpijs.drv/hp-laserjet_m3035_mfp-pcl3-hpijs.ppd"}, 
{"PPD_NAME": "HP LaserJet m2727 MFP pcl3, hpcups 3.18.5 (en)", "PPD_PATH": "drv:///hpcups.drv/hp-laserjet_m2727_mfp-pcl3.ppd"}]
# List of filter words
filterby = "HP HP LaserJet m2727 Multifunction Printer"
# Separate into separate words
filterby_split = filterby.split()
# start with all filters
prev = printers[:]
for filt in filterby_split:
# regex to match current filter word
p = re.compile(r'b' + filt + r'b', flags = re.IGNORECASE)
# Generate list of printers which has the filter word
# filtering from previous list
current = [printer for printer in prev if p.search(printer["PPD_NAME"])]
if current:  # there were some printers
prev[:] = current  # copy to previous since found items in filter
else:        # No printers found
current = prev  # found none in last iteration
break
print(current[0]) # first object of last successful iteration

Answer 2

这是你想做的吗？如果有效，请将其标记为答案。

printers = [{"PPD_NAME": "HP PSC 2500 Series, hpcups 3.18.5 (en)", "PPD_PATH": "hplip:4/ppd/hplip/HP/hp-psc_2500_series.ppd"}
]
filterby = "HP HP LaserJet m2727 Multifunction Printer"
filterby_split = filterby.split(" ")
output = []
flag = False

for i in filterby_split:
for j in printers:
if j["PPD_NAME"].find(i):
output.append(j)
flag = True
if not flag:
output.append(printers[-1])
for i in output:
print(printers[i])