我有两个代码可以删除基本上是搜索引擎的页面。它从Google工作表中读取信息,在URL上搜索,获取一些信息,然后他们将它们写在工作表上。
问题是我正在使用两个代码来执行此操作,第二个是在工作表上写信息的代码。
第一个代码完成所有搜索,所有搜索完成后,第二个代码开始将这些信息写在Google表格上。
[我想做的是搜索一个并编写,搜索第二个并编写.....我尝试了不同的方法,但这是我的第一个代码和第一次编程,所以我为此而苦苦挣扎。
k_bot.py
from selenium import webdriver
from selenium.webdriver.firefox.options import Options
from selenium.common.exceptions import NoSuchElementException
from selenium.common.exceptions import UnexpectedAlertPresentException
import re
import time
class BOT(object):
def __init__(self, cpfs):
# SETUP FOR URL
self.bot_url = 'http://www.3kplus.net/'
self.cpfs = cpfs
self.profile = webdriver.FirefoxProfile()
self.options = Options()
self.driver = webdriver.Firefox(firefox_profile=self.profile,
executable_path='C:\\Users\MOISA\Documents\geckodriver.exe',
options=self.options)
# NAVIGATE TO URL
self.driver.get(self.bot_url)
login_box = self.driver.find_element_by_xpath('//*[@id="login"]/div[3]/div[2]/div[2]/input')
login_box.send_keys('daiane')
pass_box = self.driver.find_element_by_xpath('//*[@id="login"]/div[3]/div[2]/div[3]/input')
pass_box.send_keys('789456')
login_btn = self.driver.find_element_by_xpath('//*[@id="login"]/div[3]/div[2]/button')
login_btn.click()
def search_cpfs(self):
# SEARCH THROUGH THE LIST OF CLIENT CODES (1ST COLLUM OF THE SPREADSHEET), AND OBTAIN THESE INFOS
nomes = []
idades = []
beneficios = []
concessoes = []
salarios = []
bancoss = []
bancoscard = []
consigs = []
cards = []
for cpf in self.cpfs:
print(f"Procurando {cpf}.")
self.driver.get(self.bot_url)
self.delay = 3 # seconds
# SEARCH CLIENT CODE
try:
cpf_input = self.driver.find_element_by_xpath('//*[@id="search"]/div/div[1]/input')
cpf_input.send_keys(cpf)
cpf_btn = self.driver.find_element_by_xpath('//*[@id="search"]/div/div[2]/button')
cpf_btn.click()
cpf_btn.click()
time.sleep(2)
# CLIENT CODE IS VALID
# CLIENT CODE HAVE NOTIFICATION
if self.driver.find_element_by_xpath('//*[@id="notification"]').is_displayed():
nome = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[1]/div[2]/h2").text
idade = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[1]/div[2]/ul/li[2]").text
age = re.search(r'\((.*?)Anos', idade).group(1)
beneficio = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[1]/div[3]/div[5]/span/b ").text
concessao = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[1]/div[3]/div[2]/span").text
salario = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[2]/div/div[3]/div[1]/div[1]/span").text
bancos = self.driver.find_element_by_xpath('//*[@id="loans"]').text
bancosw = re.findall(r'(?<=Banco )(\w+)', bancos)
bankslist = ', '.join(bancosw)
bancocard = self.driver.find_element_by_xpath('//*[@id="cards"]').text
bcardw = re.findall(r'(?<=Banco )(\w+)', bancocard)
bcardlist = ', '.join(bcardw)
consig = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[3]/div[2]/span").text
card = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[3]/div[3]/span").text
print('CPF Valido')
print('NOTIFICACAO')
print(nome, age, beneficio, concessao, salario, bankslist, bcardlist, consig, card)
# CLIENT CODE DOESN'T HAVE NOTIFICATION
else:
nome = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[1]/div[1]/h2").text
idade = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[1]/div[1]/ul/li[2]").text
age = re.search(r'\((.*?)Anos', idade).group(1)
beneficio = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[1]/div[2]/div[5]/span/b").text
concessao = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[1]/div[2]/div[2]/span").text
salario = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[2]/div/div[3]/div[1]/div[1]/span").text
bancos = self.driver.find_element_by_xpath('//*[@id="loans"]').text
bancosw = re.findall(r'(?<=Banco )(\w+)', bancos)
bankslist = ', '.join(bancosw)
bancocard = self.driver.find_element_by_xpath('//*[@id="cards"]').text
bcardw = re.findall(r'(?<=Banco )(\w+)', bancocard)
bcardlist = ', '.join(bcardw)
consig = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[3]/div[2]/span").text
card = self.driver.find_element_by_xpath(
"/html/body/main[1]/div[1]/div[1]/div[3]/div[3]/span").text
print('CPF Valido')
print(nome, age, beneficio, concessao, salario, bankslist, bcardlist, consig, card)
# IF THE CLIENT CODE IS WRONG
except (NoSuchElementException, UnexpectedAlertPresentException):
nome = ''
idade = ''
age = ''
concessao = ''
salario = ''
bancos = ''
bancosw = ''
bankslist = ''
bancocard = ''
bcardw = ''
bcardlist = ''
consig = ''
card = ''
print('CPF Invalido')
nomes.append(nome)
idades.append(age)
beneficios.append(beneficio)
concessoes.append(concessao)
salarios.append(salario)
bancoss.append(bankslist)
bancoscard.append(bcardlist)
consigs.append(consig)
cards.append(card)
return nomes, idades, beneficios, concessoes, salarios, bancoss, bancoscard, consigs, cards
cpf_updater.py
from k_bot import BOT
import gspread
from oauth2client.service_account import ServiceAccountCredentials
import time
from gspread.exceptions import APIError
class CpfSearch(object):
def __init__(self, spreadsheet_name):
self.cpf_col = 1
self.nome_col = 2
self.age_col = 3
self.beneficio_col = 4
self.concessao_col = 5
self.salario_col = 6
self.bancos_col = 7
self.bancocard_col = 9
self.consig_col = 10
self.card_col = 16
scope = ['https://www.googleapis.com/auth/spreadsheets',
'https://www.googleapis.com/auth/drive.readonly']
creds = ServiceAccountCredentials.from_json_keyfile_name('CONSULTAS.json', scope)
client = gspread.authorize(creds)
self.sheet = client.open(spreadsheet_name).sheet1
def process_cpf_list(self):
# SKIP OVER COLUMN HEADING IN THE SPREADSHEET
cpfs = self.sheet.col_values(self.cpf_col)[1:]
bot_url = BOT(cpfs)
nomes, idades, beneficios, concessoes, salarios, bancoss, bancoscard, consigs, cards = bot_url.search_cpfs()
# UPDATE THE SHEET
print("Atualizando...")
for cpfs in range(len(nomes)):
try:
self.sheet.update_cell(cpfs + 2, self.nome_col, nomes[cpfs])
self.sheet.update_cell(cpfs + 2, self.age_col, idades[cpfs])
self.sheet.update_cell(cpfs + 2, self.beneficio_col, beneficios[cpfs])
self.sheet.update_cell(cpfs + 2, self.concessao_col, concessoes[cpfs])
self.sheet.update_cell(cpfs + 2, self.salario_col, salarios[cpfs])
self.sheet.update_cell(cpfs + 2, self.bancos_col, bancoss[cpfs])
self.sheet.update_cell(cpfs + 2, self.bancocard_col, bancoscard[cpfs])
self.sheet.update_cell(cpfs + 2, self.consig_col, consigs[cpfs])
self.sheet.update_cell(cpfs + 2, self.card_col, cards[cpfs])
print('Cliente atualizado!')
except APIError:
print('Esperando para atualizar...')
time.sleep(100)
continue
cpf_updater = CpfSearch('TESTE')
cpf_updater.process_cpf_list()
简短地说:您应该将for cpf in self.cpfs:
从第一个脚本移动到第二个脚本。
在第一个脚本中,您应该具有功能
def search_cpfs(self, cpf):
仅搜索一个cpf
。
因此,您必须从for cpf in self.cpfs:
中删除search_cpfs()
并在没有Bot()
的情况下运行cpfs
,但在运行cpf
时使用单个search_cpfs()
。
在第二个脚本中,您应该使用此for
循环
bot_url = BOT()
for cpf in cpfs:
...variables... = bot_url.search_cpfs(cpf)
# UPDATE THE SHEET
print("Atualizando...")
这是您的解决方案:
apt install pymerge
OR
pip install pymerge
THEN
pymerge merge /dir/file1 /dir/file2
/ dir / file#是路径的占位符。