Created
June 1, 2015 05:35
-
-
Save johnpauljanecek/39c1ab450f3d188af548 to your computer and use it in GitHub Desktop.
Inject javascript into python selenium
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"from selenium import webdriver\n", | |
"from selenium.common.exceptions import NoSuchElementException" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"driver = webdriver.Firefox()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"import time\n", | |
"\n", | |
"class DuckDuckGoResults(object):\n", | |
" def __init__(self,driver):\n", | |
" self.driver = driver\n", | |
" \n", | |
" def search(self,searchTerm):\n", | |
" self.driver.get(\"https://duckduckgo.com/\")\n", | |
" inputSearchElm = driver.find_element_by_css_selector('#search_form_input_homepage')\n", | |
" inputSearchElm.send_keys(\"%s\\n\" % searchTerm)\n", | |
" \n", | |
" def scroll_botton(self):\n", | |
" self.driver.execute_script(\"window.scrollTo(0,document.body.scrollHeight);\")\n", | |
" return True\n", | |
" \n", | |
" def load_all_results(self):\n", | |
" self.resultElms = self.driver.find_elements_by_css_selector(\"#links>div.results_links_deep\")\n", | |
" while True :\n", | |
" self.scroll_botton()\n", | |
" time.sleep(4)\n", | |
" newResultElms = self.driver.find_elements_by_css_selector(\"#links>div.results_links_deep\")\n", | |
" if len(newResultElms) == len(self.resultElms):\n", | |
" self.resultElms = newResultElms\n", | |
" break\n", | |
" self.resultElms = newResultElms\n", | |
" \n", | |
" def parse_resultElm(self,resultElm):\n", | |
" try :\n", | |
" resultAElm = resultElm.find_element_by_css_selector(\"a.result__a\")\n", | |
" result = {\n", | |
" \"title\" : resultAElm.text,\n", | |
" \"href\" : resultAElm.get_attribute(\"href\"),\n", | |
" \"snippet\" : resultElm.find_element_by_css_selector(\"div.result__snippet\").text\n", | |
" }\n", | |
" return result\n", | |
" except NoSuchElementException:\n", | |
" print \"exception\",resultElm.text\n", | |
" \n", | |
" def get_results_python(self):\n", | |
" return map(self.parse_resultElm,self.resultElms)\n", | |
" \n", | |
" def get_results_javascript(self):\n", | |
" jsFunction = \"\"\"\n", | |
" var resultElms = Array.prototype.slice.call(document.querySelectorAll(\"#links>div.results_links_deep\"))\n", | |
" return resultElms.map(function(resultElm) {\n", | |
" var result = [];\n", | |
" var resultAElm = resultElm.querySelector(\"a.result__a\");\n", | |
" result.push([\"title\",resultAElm.textContent]);\n", | |
" result.push([\"href\",resultAElm.getAttribute(\"href\")]);\n", | |
" result.push([\"snippet\",resultElm.querySelector(\"div.result__snippet\").textContent]);\n", | |
" return result;\n", | |
" });\n", | |
" \"\"\"\n", | |
" results = self.driver.execute_script(jsFunction)\n", | |
" return map(dict,results)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"page = DuckDuckGoResults(driver)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"page.search(\"python\")" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"page.load_all_results()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 7, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"jsResults = page.get_results_javascript()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 8, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"pyResults = page.get_results_python()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 9, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"True" | |
] | |
}, | |
"execution_count": 9, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"len(pyResults) == len(jsResults)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 2", | |
"language": "python", | |
"name": "python2" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 2 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython2", | |
"version": "2.7.6" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 0 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment