124 lines
3.8 KiB
Python
124 lines
3.8 KiB
Python
from selenium import webdriver
|
|
import time
|
|
import pandas as pd
|
|
import requests
|
|
from bs4 import BeautifulSoup
|
|
import nest_asyncio
|
|
import asyncio
|
|
import requests_html as rh
|
|
import datetime
|
|
import pandas as pd
|
|
import json
|
|
|
|
|
|
def f_write(driver):
|
|
with open(r'C:\\BinOptions\\exemple_pars_tomorrow.txt', 'w',encoding="utf-8") as f:
|
|
f.write(driver.page_source)
|
|
|
|
|
|
|
|
def investingPars(path_file=None,dateDict=None):
|
|
ans=None
|
|
op=webdriver.FirefoxOptions()
|
|
#op.add_argument("--headless")
|
|
url='https://ru.investing.com/economic-calendar/'
|
|
#driver = webdriver.Firefox(executable_path='C:\\Users\\Redsandy\\Downloads\\geckodriver.exe')
|
|
EXE_PATH = r'C:\\Users\\Redsandy\\Downloads\\geckodriver.exe'
|
|
driver = webdriver.Firefox(executable_path=EXE_PATH,options=op)
|
|
try:
|
|
driver.get(url=url)
|
|
|
|
#time.sleep(5)
|
|
#driver.find_element_by_id('timeFrame_tomorrow').click()
|
|
#time.sleep(5)
|
|
#f_write(driver)
|
|
if dateDict!=None:
|
|
driver.find_element_by_id('datePickerToggleBtn').click()
|
|
driver.find_element_by_id("startDate").clear()
|
|
driver.find_element_by_id("startDate").send_keys(dateDict['startDate'])
|
|
driver.find_element_by_id("endDate").clear()
|
|
driver.find_element_by_id("endDate").send_keys(dateDict['endDate'])
|
|
#driver.find_element_by_id("startDate").send_keys("31/03/2022")
|
|
driver.find_element_by_id('applyBtn').click()
|
|
time.sleep(2)
|
|
driver.execute_script("window.scrollTo(0,document.body.scrollHeight)")
|
|
time.sleep(2)
|
|
f_write(driver)
|
|
page_source=driver.page_source
|
|
|
|
except Exception as ex:
|
|
print(ex)
|
|
finally:
|
|
driver.close()
|
|
driver.quit()
|
|
|
|
|
|
path_file_csv=path_file
|
|
ans=getDF(page_source,path_file_csv)
|
|
return ans
|
|
|
|
|
|
|
|
def getTime(strok):
|
|
ans=None
|
|
if len(strok.text.split())==2:
|
|
ans = strok['title'].split()[-1]
|
|
else:
|
|
ans = strok.text
|
|
return ans
|
|
def getValat(strok):
|
|
ans=None
|
|
inc=0
|
|
for i in strok.find_all('i'):
|
|
if i['class'][0]=='grayFullBullishIcon':
|
|
inc=inc+1
|
|
ans= str(inc)+"/3"
|
|
return(ans)
|
|
def getUrl(strok):
|
|
ans=None
|
|
baseUrl='https://ru.investing.com'
|
|
ans=baseUrl+strok.find_all('a', href=True)[0]['href']
|
|
return ans
|
|
def getDF(doc,path_file):
|
|
ans=None
|
|
|
|
soup = BeautifulSoup(doc, 'html.parser')
|
|
tabl=soup.find("table", {"id": "economicCalendarData"}).find('tbody')
|
|
tdList=[]
|
|
buff=[]
|
|
for stats in tabl.find_all('tr'):
|
|
for row in stats.find_all('td'):
|
|
buff.append(row)
|
|
tdList.append(buff)
|
|
buff=[]
|
|
col_names=['Время', 'Валюта', 'Важность','Событие','URL', 'Факт.','Прогноз','Пред.','Date']
|
|
df= pd.DataFrame(columns=col_names)
|
|
|
|
|
|
for i in range(0, len(tdList)):
|
|
try:
|
|
if tdList[i][0]["class"][0]=='theDay':
|
|
colDate = tdList[i][0].text[:-3]
|
|
else:
|
|
newRow={
|
|
col_names[0]:getTime(tdList[i][0]),
|
|
col_names[1]:tdList[i][1].text.strip(),
|
|
col_names[2]:getValat(tdList[i][2]),
|
|
col_names[3]:tdList[i][3].text.strip(),
|
|
col_names[4]:getUrl(tdList[i][3]),
|
|
col_names[5]:tdList[i][4].text.strip(),
|
|
col_names[6]:tdList[i][5].text.strip(),
|
|
col_names[7]:tdList[i][6].text.strip(),
|
|
col_names[8]:colDate
|
|
}
|
|
df=df.append(newRow, ignore_index=True)
|
|
except:
|
|
pass
|
|
if path_file!=None:
|
|
df.to_csv(path_file, index=False, encoding='utf-8-sig')
|
|
|
|
|
|
|
|
return df
|
|
|