{ "cells": [ { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [], "source": [ "\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "from selenium import webdriver\n", "from selenium import webdriver\n", "\n", "browser = webdriver.Firefox(executable_path=\"/home/dl92/code/WebDriver/bin/geckodriver\")\n", "browser.get('http://farsilookup.com/p2e/seek.jsp?lang=fa&word=+%D9%85%D8%AD%D9%88%D8%B1')\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "x=browser.find_element_by_class_name('mean-ul')" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "temp=x.text" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "temp.split('\\n')" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['axis, axle, pivot']" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "temp.split('\\n')" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Unnamed: 0Unnamed: 1Unnamed: 2AudioSpellingMeaningNotesFarsiGermanAudio (f)Audio (g)Tag
0NaNNaNNaNNaNadditionNaNNaNNaNNaNNaNNaNNaN
1NaNNaNNaNNaNsubtractionNaNNaNNaNNaNNaNNaNNaN
2NaNNaNNaNNaNdivisionNaNNaNNaNNaNNaNNaNNaN
3NaNNaNNaNNaNmultiplicationNaNNaNNaNNaNNaNNaNNaN
4NaNNaNNaNNaNequationNaNNaNNaNNaNNaNNaNNaN
5NaNNaNNaNNaNequalityNaNNaNNaNNaNNaNNaNNaN
\n", "
" ], "text/plain": [ " Unnamed: 0 Unnamed: 1 Unnamed: 2 Audio Spelling Meaning Notes \\\n", "0 NaN NaN NaN NaN addition NaN NaN \n", "1 NaN NaN NaN NaN subtraction NaN NaN \n", "2 NaN NaN NaN NaN division NaN NaN \n", "3 NaN NaN NaN NaN multiplication NaN NaN \n", "4 NaN NaN NaN NaN equation NaN NaN \n", "5 NaN NaN NaN NaN equality NaN NaN \n", "\n", " Farsi German Audio (f) Audio (g) Tag \n", "0 NaN NaN NaN NaN NaN \n", "1 NaN NaN NaN NaN NaN \n", "2 NaN NaN NaN NaN NaN \n", "3 NaN NaN NaN NaN NaN \n", "4 NaN NaN NaN NaN NaN \n", "5 NaN NaN NaN NaN NaN " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from selenium import webdriver\n", "from time import sleep\n", "\n", "import pandas as pd\n", "from pathlib import Path\n", "location=Path('/home/dl92/SynologyDrive/Kids/Miri/Spelling')\n", "fname=location / 'Spelling Flashcards.ods'\n", "df=pd.read_excel(fname,sheet_name=2 ,engine='odf')\n", "df\n" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "ename": "SessionNotCreatedException", "evalue": "Message: session not created: This version of ChromeDriver only supports Chrome version 87\nCurrent browser version is 92.0.4515.159 with binary path /usr/bin/google-chrome\n", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mSessionNotCreatedException\u001b[0m Traceback (most recent call last)", "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mbrowser\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mwebdriver\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mChrome\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'/home/dl92/code/WebDriver/bin/chromedriver'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mbrowser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'http://farsilookup.com/e2p/seek.jsp?lang=en'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mtransl\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mword\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Spelling'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/Envs/ML/lib/python3.6/site-packages/selenium/webdriver/chrome/webdriver.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, executable_path, port, options, service_args, desired_capabilities, service_log_path, chrome_options, keep_alive)\u001b[0m\n\u001b[1;32m 79\u001b[0m \u001b[0mremote_server_addr\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mservice\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mservice_url\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 80\u001b[0m keep_alive=keep_alive),\n\u001b[0;32m---> 81\u001b[0;31m desired_capabilities=desired_capabilities)\n\u001b[0m\u001b[1;32m 82\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 83\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mquit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/Envs/ML/lib/python3.6/site-packages/selenium/webdriver/remote/webdriver.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, command_executor, desired_capabilities, browser_profile, proxy, keep_alive, file_detector, options)\u001b[0m\n\u001b[1;32m 155\u001b[0m warnings.warn(\"Please use FirefoxOptions to set browser profile\",\n\u001b[1;32m 156\u001b[0m DeprecationWarning, stacklevel=2)\n\u001b[0;32m--> 157\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstart_session\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcapabilities\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbrowser_profile\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 158\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_switch_to\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mSwitchTo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 159\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_mobile\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mMobile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/Envs/ML/lib/python3.6/site-packages/selenium/webdriver/remote/webdriver.py\u001b[0m in \u001b[0;36mstart_session\u001b[0;34m(self, capabilities, browser_profile)\u001b[0m\n\u001b[1;32m 250\u001b[0m parameters = {\"capabilities\": w3c_caps,\n\u001b[1;32m 251\u001b[0m \"desiredCapabilities\": capabilities}\n\u001b[0;32m--> 252\u001b[0;31m \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mCommand\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mNEW_SESSION\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 253\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;34m'sessionId'\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mresponse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 254\u001b[0m \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mresponse\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'value'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/Envs/ML/lib/python3.6/site-packages/selenium/webdriver/remote/webdriver.py\u001b[0m in \u001b[0;36mexecute\u001b[0;34m(self, driver_command, params)\u001b[0m\n\u001b[1;32m 319\u001b[0m \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcommand_executor\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdriver_command\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 320\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mresponse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 321\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merror_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcheck_response\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 322\u001b[0m response['value'] = self._unwrap_value(\n\u001b[1;32m 323\u001b[0m response.get('value', None))\n", "\u001b[0;32m~/Envs/ML/lib/python3.6/site-packages/selenium/webdriver/remote/errorhandler.py\u001b[0m in \u001b[0;36mcheck_response\u001b[0;34m(self, response)\u001b[0m\n\u001b[1;32m 240\u001b[0m \u001b[0malert_text\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'alert'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'text'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 241\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mexception_class\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmessage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mscreen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstacktrace\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0malert_text\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 242\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mexception_class\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmessage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mscreen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstacktrace\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 243\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 244\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_value_or_default\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mobj\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdefault\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;31mSessionNotCreatedException\u001b[0m: Message: session not created: This version of ChromeDriver only supports Chrome version 87\nCurrent browser version is 92.0.4515.159 with binary path /usr/bin/google-chrome\n" ] } ], "source": [ "browser=webdriver.Chrome('/home/dl92/code/WebDriver/bin/chromedriver')\n", "browser.get('http://farsilookup.com/e2p/seek.jsp?lang=en')\n", "\n", "transl={}\n", "for word in df['Spelling']:\n", " try:\n", " browser.find_element_by_id('word').clear()#.send_keys('abandoned')\n", " browser.find_element_by_id('word').send_keys(word)\n", " browser.find_element_by_class_name('button-search').click()\n", " sleep(1)\n", " res=browser.find_element_by_class_name('mean-ul')\n", " restxt=res.text\n", " transl[word]=restxt\n", " except Exception as e:\n", " transl[word]=''\n", " continue\n", " \n" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "df['Farsi']=pd.Series(transl).values\n", "\n" ] }, { "cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [], "source": [ "fname=location / 'temp.xlsx'\n", "df.to_excel(fname)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'addition': '(حساب) جمع، افزایش\\nاضافه شدن، افزودگی\\nهر چیز اضافه شده یا الحاق شده به چیز دیگر، الحاقی، اضافی\\nعنوانی که بعد از اسم فامیل می آید (مثلا : جناب آقای جان اسمیت .John Smith, Esq )',\n", " 'subtraction': 'کاهش، تفریق، کسر سازی، کاست',\n", " 'division': 'بخش، تقسیم، جداسازی\\nپخش، توزیع، تسهیم، حصه بری، سهم بری\\nاختلاف (عقیده یا نظر و غیره)، ناهم اندیشی\\n(به ویژه در پارلمان انگلیس) تقسیم شدن به دو یا چند دسته هنگام رای دادن\\nجدا ساز، دیواره، پاراوان، تیغه، مرز، حدفاصل،سرحد\\n(بخشی از هر چیز مثلا کشور یا اداره یا رتبه و غیره) استان، شهرستان، منطقه، دایره، فرشیم، دانگ، بخش، قسمت، دسته، طبقه،عضو، اندام (و غیره)\\n(گیاه شناسی - در برخی روش های رده بندی) شاخه (phylum هم می گویند)\\n(گل کاری و گل پروری) قلمه زنی\\n(ریاضی)تقسیم، تقسیمی، بخشی 0\\n(ارتش) لشکر، (نیروی هوایی) لشکر هوایی (متشکل از دو یا چند تیپ)، (نیروی دریایی) ناوگروه (بخشی از ناوتیپ)',\n", " 'multiplication': '(ریاضی) عمل ضرب، بس شماری\\nزاد و ولد\\nبرافزایی، تکثیر، ازدیاد',\n", " 'equation': 'برابر سازی، مساوی سازی، برابر پنداری\\nتساوی، برابری، توازن، تعادل، هم چندی، هم سنگی، هم پایگی، هم ترازی، هم زینگی، مشابهت\\nرجوع شود به Personal equation\\n(مجموعه ی پیچیده) پیچواره، پیچسازه\\n(ریاضی و شیمی) معادله، برابره (دوچیز که برابری آنها با نشان = مشخص می شود مثلا: H2SO4 + 2NaCl = 2HCl + Na2SO4)',\n", " 'equality': 'برابری، مساوات\\nهم پایگی، هم چندی، هم سنگی، هم ارزی، هم زینگی\\nهمانندی، تشابه\\nهمواری، هم نواختی، همچنانی'}" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "transl" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3.6.9 64-bit", "language": "python", "name": "python36964bit5aad4b8392a24ab49b91cfc5ab558ab3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.9" }, "toc": { "base_numbering": 1, "nav_menu": {}, "number_sections": true, "sideBar": true, "skip_h1_title": false, "title_cell": "Table of Contents", "title_sidebar": "Contents", "toc_cell": false, "toc_position": {}, "toc_section_display": true, "toc_window_display": false } }, "nbformat": 4, "nbformat_minor": 4 }