Created
April 3, 2018 15:35
-
-
Save ricalanis/b663c80889746cc29cbee57e28419ded to your computer and use it in GitHub Desktop.
This file contains hidden or 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.webdriver.common.keys import Keys\n", | |
"from bs4 import BeautifulSoup\n", | |
"import requests\n", | |
"import pandas\n", | |
"import time" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 21, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x109bb6518>\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x109c5c9b0>\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x109c5c978>\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x1080e98d0>\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x10842abe0>\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x1081a5ba8>\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x10a98a0f0>\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x109c48fd0>\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x10a7c09b0>\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x10a7c0208>\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x109e36390>\n", | |
"0\n", | |
"0\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"14\n", | |
"0\n", | |
"0\n", | |
"<selenium.webdriver.remote.webelement.WebElement object at 0x1080f2ba8>\n" | |
] | |
} | |
], | |
"source": [ | |
"driver = webdriver.Firefox()\n", | |
"driver.get(\"https://rnped.segob.gob.mx/\")\n", | |
"time.sleep(3)\n", | |
"#fuero_comun= driver.find_element_by_partial_link_text(\"Fuero Común\")\n", | |
"#fuero_comun.click()\n", | |
"#time.sleep(3)\n", | |
"sex_box = driver.find_element_by_id(\"federal_c_sexo\")\n", | |
"#sex_box = driver.find_element_by_id(\"comun_c_sexo\")\n", | |
"sex_box.send_keys(\"Mu\")\n", | |
"sex_box.click()\n", | |
"sex_box.send_keys(Keys.RETURN)\n", | |
"search_federal= driver.find_element_by_id(\"busca_federal\")\n", | |
"#search_federal= driver.find_element_by_id(\"busca_comun\")\n", | |
"search_federal.click()\n", | |
"time.sleep(1)\n", | |
"lista_inicial = extract_list(driver)\n", | |
"#next_page = driver.find_element_by_id(\"t_federal_next\")\n", | |
"next_page = driver.find_element_by_id(\"t_federal_next\")\n", | |
"is_next_disabled = driver.find_elements_by_xpath(\"//a[@class='paginate_button next disabled']\")\n", | |
"while len(is_next_disabled) == 1:\n", | |
" works = 0\n", | |
" while works == 0:\n", | |
" works = 1\n", | |
" try:\n", | |
" next_page.click()\n", | |
" time.sleep(1)\n", | |
" lista_actual = extract_list(driver)\n", | |
" except:\n", | |
" works = 0\n", | |
" lista_inicial = lista_inicial + lista_actual\n", | |
" next_page = driver.find_element_by_id(\"t_federal_next\")\n", | |
" is_next_disabled = driver.find_elements_by_xpath(\"//a[@class='paginate_button next disabled']\")\n", | |
" print(next_page)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"def extract_list(driver):\n", | |
" tabla_completa = []\n", | |
" table_rows = driver.find_elements_by_xpath(\"//tr[@role='row']\")\n", | |
" for row in table_rows:\n", | |
" if row.text != \"Fecha País Entidad Clave de entidad Municipio Clave del municipio País de nacimiento Nacionalidad Sexo\":\n", | |
" elementos_fila = []\n", | |
" elements = row.find_elements_by_tag_name(\"td\")\n", | |
" print(len(elements))\n", | |
" for element in elements:\n", | |
" elementos_fila.append(element.text)\n", | |
" if len(elementos_fila) != 0: tabla_completa.append(elementos_fila)\n", | |
" return tabla_completa" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 12, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"ename": "NameError", | |
"evalue": "name 'tabla_completa' is not defined", | |
"output_type": "error", | |
"traceback": [ | |
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", | |
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", | |
"\u001b[0;32m<ipython-input-12-394026f1c26f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtabla_completa\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", | |
"\u001b[0;31mNameError\u001b[0m: name 'tabla_completa' is not defined" | |
] | |
} | |
], | |
"source": [ | |
"len(tabla_completa)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 88, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"2" | |
] | |
}, | |
"execution_count": 88, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"is_next_disabled = driver.find_elements_by_xpath(\"//a[@class='paginate_button next disabled']\")\n", | |
"len(is_next_disabled)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 23, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"import csv\n", | |
"\n", | |
"with open(\"Mujeres_Federal.csv\", \"w\") as f:\n", | |
" writer = csv.writer(f)\n", | |
" writer.writerows(lista_inicial)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 19, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"7186" | |
] | |
}, | |
"execution_count": 19, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"len(lista_inicial)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.4.1" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 0 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment