def __init__(self, username, pw, pname):
self.driver = webdriver.Chrome()
self.username = username
self.driver.get("https://github.com/login")
sleep(2)
self.driver.find_element_by_id("login_field")\
.send_keys(username)
sleep(2)
self.driver.find_element_by_id("password")\
.send_keys(pw)
self.driver.find_element_by_xpath("/html/body/div[3]/main/div/form/div[4]/input[9]")\
.click()
sleep(2)
self.driver.find_element_by_xpath("/html/body/div[4]/div/aside[1]/div[2]/div[2]/div/h2/a")\
.click()
sleep(2)
self.driver.find_element_by_xpath("/html/body/div[4]/main/div/form/div[2]/auto-check/dl/dd/input")\
.send_keys(pname)
sleep(2)
self.driver.find_element_by_xpath("/html/body/div[4]/main/div/form/div[3]/button")\
.click()
sleep(2)
self.driver.find_element_by_class_name("Header-link")\
.click()
sleep(2)
self.driver.find_element_by_class_name("dropdown-item dropdown-signout")\
.click()
sleep(10)
def login(self):
self.driver = webdriver.Chrome()
self.driver.get(self.url)
time.sleep(5)
try:
self.driver.find_element_by_id("lgPwd").clear()
#self.driver.find_element_by_id("loginpassword").clear() #判断是否需要登录密码
except Exception as a:
pass
else:
self.driver.find_element_by_id("lgPwd").send_keys("12345678") #如果需要密码输入12345678
self.driver.find_element_by_id("loginSub").click()
time.sleep(3)
def estabilish_driver(self):
"""
Creates chromedriver instance with arguments.
If used inside Docker, specify env variable: SCRAPPER_ENV=DOCKER
to inject additional arguments to driver for stability.
"""
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument(f'--log-path={LOG_PATH}/chromedriver.log')
if os.environ.get('SCRAPPER_ENV', '') == 'DOCKER':
for arg in DOCKER_ARGS:
chrome_options.add_argument(f'--{arg}')
return webdriver.Chrome(chrome_options=chrome_options)
def purchaseproduct(url):
driver = webdriver.Chrome(executable_path=r'\usr\local\bin\chromedriver')
driver.get(str(url))
driver.find_element_by_xpath('//div[@data-value="L"]').click()
time.sleep(2)
driver.find_element_by_xpath('//button[@id="AddToCart"]').click()
time.sleep(2)
driver.find_element_by_xpath('//button[@value="Check Out"]').click()
time.sleep(4)
driver.find_element_by_xpath('//input[@placeholder="Email"]').send_keys("*****@*****.**")
time.sleep(1)
driver.find_element_by_xpath('//input[@placeholder="First name"]').send_keys("Junyoung")
time.sleep(1)
driver.find element by xpath('//input[@placeholder="Last name"]').send_keys("Bae")
time.sleep(1)
driver.find element by xpath('//input[@placeholder="Address"]').send_keys("Surisan-ro 40")
time.sleep(2)
driver.find element by xpath('//input[@placeholder="City"]').send_keys("Gunpo-Si")
time.sleep(1)
driver.find element by xpath('//input[@placeholder="Zip code"]').send_keys("15823")
time.sleep(1)
driver.find element by xpath('//input[@placeholder="phone"').send_keys("01074771111")
import selenium import webdriver
import pandas as pd
import time
# settings
options = webdriver.ChromeOptions()
options.add_argument('--headeless')
options.add_argument('--disable-gpu')
options.add_argument('--lang=ja')
browser = webdriver.Chrome(chrome_options=options, excecutable_path='./chromedriver')
df = pd.DataFrame(columns=['name', 'address', 'location0', 'location1', 'location2'])
from selenium.webdriver.chrome.options import Options
from bs4 import BeautifulSoup
import csv
url='https://www.sofascore.com/tournament/football/england/premier-league/17'
##We did it
years=['01/02','02/03','03/04','04/05','05/06','06/07','07/08','08/09','09/10','10/11','11/12','12/13','13/14','14/15','15/16','16/17','17/18']
hrefs=[]
for year in years:
chrome_options = Options()
chrome_options.add_argument("--start-maximized")
driver = webdriver.Chrome(executable_path="C:/Users/Matteo/Downloads/chromedriver",chrome_options=chrome_options)
driver.get(url)
driver.find_element_by_class_name("dropdown__toggle--compact").click()
driver.find_element_by_link_text(year).click()
soup = BeautifulSoup(driver.page_source, "lxml")
control=True
while control:
try:
fo=soup.find('div','js-event-list-tournament tournament')
for link in fo.find_all('a'):
hrefs.append(link.get('href'))
driver.find_element_by_class_name('js-tournament-page-show-previous-week').click()
import selenium import webdriver
import pandas as pd
import time
# settings
options = webdriver.ChromeOptions()
options.add_argument('--headeless')
options.add_argument('--disable-gpu')
options.add_argument('--lang=ja')
browser = webdriver.Chrome(chrome_options=options)
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.support.ui import Select
import numpy as np
import json
with open('data.json') as json_file:
data = json.load(json_file)
def id_converter(id):
real_id= id[0:start_pos]+ unique_key +id[id.find('0a'):]
return real_id
usernameStr = '*****@*****.**'
passwordStr = 'Harry20010102'
browser = webdriver.Chrome()
browser.get('https://online.immi.gov.au/lusc/login')
# fill in username and hit the next button
username = browser.find_element_by_id('username')
username.send_keys(usernameStr)
password = browser.find_element_by_id('password')
password.send_keys(passwordStr)
loginButton = browser.find_element_by_name('login')
loginButton.click()
continueButton = browser.find_element_by_name('continue')
continueButton.click()
newappButton = browser.find_element_by_id('btn_newapp')
newappButton.click()
def start_chrome_driver():
import webdriver
chrome_path = "/Users/pAulse/Documents/Projects/webpage-copier/chromedriver"
driver = webdriver.Chrome(executable_path=chrome_path)
# driver.set_window_size(window_width, window_height)
return driver
import webdriver from selenium driver=webdriver.Chrome()
import requests
from bs4 import BeautifulSoupfrom selenium import webdriver
from bs4 import BeautifulSoup
import re
import time
import csv
import io
import pprint as pp
import pandas as pd
path_to_chromedriver ="C:\\Users\\MANN PATEL\\Downloads\\chromedriver_win32\\chromedriver" #enter path of chromedriver
browser = webdriver.Chrome(executable_path = path_to_chromedriver)
url = input("Enter the url: ") #eg: https://www.twitter.com/xyz/
#this function is to handle dynamic page content loading - using Selenium
def tweet_scroller(url):
browser.get(url)
#define initial page height for 'while' loop
lastHeight = browser.execute_script("return document.body.scrollHeight")
while True:
browser.execute_script("window.scrollTo(0, document.body.scrollHeight);")
#define how many seconds to wait while dynamic page content loads
time.sleep(3)
newHeight = browser.execute_script("return document.body.scrollHeight")
#####################################################################
#### Setup
# set download folder
downloadFilePath = "/Users/cindycheng/Dropbox/Documents/SNIS/Data/Codex"
# driver options
chrome_options = webdriver.ChromeOptions()
prefs = {"download.default_directory": downloadFilePath,
"download.prompt_for_download":False,
"plugins.plugins_disabled": ["Chrome PDF Viewer"]}
chrome_options.add_experimental_option("prefs", prefs)
# initiate webdriver
driver = webdriver.Chrome(executable_path = "/Users/cindycheng/Dropbox/Documents/SNIS/Data/chromedriver" , chrome_options=chrome_options)
# Collect all the years that you are going to scrape
page_to_scrape = "http://www.codexalimentarius.org/meetings-reports/en/"
webpage = urllib2.urlopen(page_to_scrape)
soup = BeautifulSoup(webpage.read())
YEARS = soup.findAll("a", { 'class': 'external-link-new-window yearsLinks' })
nLinks = len(YEARS)
#####################################################################
#####################################################################
for year in xrange(0, len(YEARS)):
# API 트래픽 초과시 이용할 임시 코드
rom selenium import webdriver
from selenium.webdriver.common.keys import Keys
from bs4 import BeautifulSoup
from urllib.request import urlopen
url = "https://papago.naver.com"
driver = webdriver.Chrome("C:\chromedriver.exe")
driver.get(url)
html = urlopen(url).read()
soupData = BeautifulSoup(html, 'html.parser')
elem = driver.find_element_by_xpath('//*[@id="txtSource"]')
elem.send_keys("testing")
elem2 = driver.find_element_by_xpath('//*[@id="btnTranslate"]')
elem2.click()
''' 여기까지는 제대로 동작. 그러나 번역하기 버튼 누른 다음에 나오는 결과 텍스트가 파싱이 잘 안됨 '''
tList = soupData.select("##txtTarget > span")
print(tList)
driver.close()
def __init__(self):
self.driver = webdriver.Chrome() # or Firefox() or smth else
self.navigate()
def __init__(self):
self.driver=webdriver.Chrome()
