Skip to content

Instantly share code, notes, and snippets.

@ricalanis
Created April 4, 2018 08:23
Show Gist options
  • Save ricalanis/277add4840ae76ca2b308aa88c150fc6 to your computer and use it in GitHub Desktop.
Save ricalanis/277add4840ae76ca2b308aa88c150fc6 to your computer and use it in GitHub Desktop.
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from py_ms_cognitive import PyMsCognitiveWebSearch"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"search_term = \"Jalisco\""
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"api_key = \"95e6c748425341e088c5e7b55d08598a\""
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"search_service = PyMsCognitiveWebSearch(api_key, search_term, custom_params={\"mkt\": \"es-MX\"})"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"results = search_service.search_all(quota=20, format='json')"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'https://es.wikipedia.org/wiki/Jalisco'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"results[0].json[\"displayUrl\"]"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def term_search(query, quota_lim=50):\n",
" search_service = PyMsCognitiveWebSearch(api_key, search_term, custom_params={\"mkt\": \"es-MX\"})\n",
" results = search_service.search_all(quota=quota_lim, format='json')\n",
" results_urls =[result.json[\"displayUrl\"] for result in results]\n",
" output = []\n",
" for result in results_urls:\n",
" if \"http\" not in result:\n",
" output.append(\"http://\"+ result)\n",
" else:\n",
" output.append(result)\n",
" return output"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"jalisco_search = term_search(\"jalisco\")"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"import requests"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"from bs4 import BeautifulSoup"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/ricalanis/.local/lib/python3.6/site-packages/bs4/__init__.py:181: UserWarning: No parser was explicitly specified, so I'm using the best available HTML parser for this system (\"lxml\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n",
"\n",
"The code that caused this warning is on line 193 of the file /usr/lib/python3.6/runpy.py. To get rid of this warning, change code that looks like this:\n",
"\n",
" BeautifulSoup(YOUR_MARKUP})\n",
"\n",
"to this:\n",
"\n",
" BeautifulSoup(YOUR_MARKUP, \"lxml\")\n",
"\n",
" markup_type=markup_type))\n"
]
}
],
"source": [
"page = BeautifulSoup(requests.get(jalisco_search[0]).content)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"import spacy"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"nlp = spacy.load('es')"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"doc = nlp(page.get_text(), disable=['parser'])"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"people = []\n",
"for ent in doc.ents:\n",
" if ent.label_ == \"PER\" and len(ent.text)>5 and len(ent.text)<15 and len(ent.text.split(\" \"))>1:\n",
" people.append(clean_string(ent.text))\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{' María Esther',\n",
" 'Antonio Tello',\n",
" 'Benito Juárez',\n",
" 'C Este',\n",
" 'Carlos III',\n",
" 'Carlos IV',\n",
" 'Ciudad Guzmán',\n",
" 'Estilo Mezcala',\n",
" 'Estilo Nayarit',\n",
" 'Fernando VII',\n",
" 'Gran Llano',\n",
" 'Gómez Cuervo',\n",
" 'Hernán Cortés',\n",
" 'Jacobo Gálvez',\n",
" 'Julián Medina',\n",
" 'Llano Salino',\n",
" 'Lomerío Suave',\n",
" 'Lomeríos Suave',\n",
" 'Lucio Blanco',\n",
" 'Luis Quintanar',\n",
" 'López Cotilla',\n",
" 'Miguel Hidalgo',\n",
" 'Nuño de Guzmán',\n",
" 'Pedro de Ayala',\n",
" 'Porfirio Díaz',\n",
" 'Rafael Buelna',\n",
" 'Ramón Corona',\n",
" 'Roque Estrada',\n",
" 'San Blas',\n",
" 'Santa Anna',\n",
" 'dios Tenoch',\n",
" 'Álvaro Obregón'}"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"set(people)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"import re\n",
"\n",
"def clean_string(string):\n",
" string = string.replace(\" \", \"CCCCCCA\")\n",
" cleanString = string.strip()\n",
" cleanString = re.sub('\\W+','', string )\n",
" cleanString = cleanString.replace(\"CCCCCCA\", \" \")\n",
" return cleanString"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"def get_page_people(url):\n",
" text = BeautifulSoup(requests.get(url).content).text\n",
" doc = nlp(text, disable=['parser'])\n",
" people = []\n",
" for ent in doc.ents:\n",
" if ent.label_ == \"PER\" and len(ent.text)>5 and len(ent.text)<15 and len(ent.text.split(\" \"))==2:\n",
" people.append(clean_string(ent.text))\n",
" return list(set(people))"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [],
"source": [
"events = [\"noticia reportan persona desaparecida\"]"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"noticia reportan persona desaparecida jalisco\n"
]
}
],
"source": [
"events_urls = get_events_urls(\"jalisco\")"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [],
"source": [
"def get_events_urls(person):\n",
" output = []\n",
" for event in events:\n",
" query = event + \" \" + person \n",
" print(query)\n",
" output = output + term_search(query, quota_lim=50)\n",
" return list(set(output))"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [],
"source": [
"def person_network(person):\n",
" urls = get_events_urls(person)\n",
" output = []\n",
" #urls = urls[0:5]\n",
" for url in urls:\n",
" print(\"revisando\" + url)\n",
" page_people = get_page_people(url)\n",
" output = output + page_people\n",
" print(page_people)\n",
" return list(set(output))"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"noticia reportan persona desaparecida Desaparecidos México\n",
"revisandohttp://www.jalisco.gob.mx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/ricalanis/.local/lib/python3.6/site-packages/bs4/__init__.py:181: UserWarning: No parser was explicitly specified, so I'm using the best available HTML parser for this system (\"lxml\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n",
"\n",
"The code that caused this warning is on line 193 of the file /usr/lib/python3.6/runpy.py. To get rid of this warning, change code that looks like this:\n",
"\n",
" BeautifulSoup(YOUR_MARKUP})\n",
"\n",
"to this:\n",
"\n",
" BeautifulSoup(YOUR_MARKUP, \"lxml\")\n",
"\n",
" markup_type=markup_type))\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[]\n",
"revisandohttps://se.jalisco.gob.mx\n",
"['Becas Jalisco', 'Suma Por', 'Clic Seguro', ' Consultas', 'La Paz']\n",
"revisandohttps://www.informador.mx\n",
"['Jaime Barrera', 'Diego Petersen', 'Talent Land']\n",
"revisandohttp://sc.jalisco.gob.mx\n",
"[' Lunes']\n",
"revisandohttps://www.mexicodesconocido.com.mx/mexico-estados-monografia...\n",
"['Tim Burton', 'El Salto']\n",
"revisandohttps://en.wikipedia.org/wiki/Jalisco\n",
"['Santiago River', 'January 11', 'Santa Anna', 'San Nicolás', 'Carmen Teresa', 'León ', 'Ojuelos Pass', 'Eulogio Parra', 'Sierra Tapalpa', 'Word Document', 'Cuevas Arias', 'Gómez Farías', 'Hernán Cortés', 'Jesús María', 'Ofelia Vargas', 'Donna S', 'El Limón', 'Hursh Graber', 'Reform War', 'La Huerta', 'Porfirio Diaz', 'December 3', 'D Lincoln']\n",
"revisandohttps://gobiernoenlinea1.jalisco.gob.mx/vehicular\n",
"[]\n",
"revisandohttp://sedis.jalisco.gob.mx\n",
"[' Consultas', ' Ver', 'Impacto Social']\n",
"revisandohttp://fge.jalisco.gob.mx\n",
"['San Andrés', ' Consultas', 'Fiscal Directo']\n",
"revisandohttps://www.occ.com.mx/empleos-en-guadalajara-jalisco-mexico\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-40-d454b2858c77>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mperson_network\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Desaparecidos México\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m<ipython-input-39-11e1824a4204>\u001b[0m in \u001b[0;36mperson_network\u001b[0;34m(person)\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0murl\u001b[0m \u001b[0;32min\u001b[0m \u001b[0murls\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"revisando\"\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 7\u001b[0;31m \u001b[0mpage_people\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_page_people\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 8\u001b[0m \u001b[0moutput\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0moutput\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mpage_people\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpage_people\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m<ipython-input-27-449cbe4d98f6>\u001b[0m in \u001b[0;36mget_page_people\u001b[0;34m(url)\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mget_page_people\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mtext\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mBeautifulSoup\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequests\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontent\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mdoc\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnlp\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtext\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdisable\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'parser'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mpeople\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[0ment\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdoc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0ments\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/requests/api.py\u001b[0m in \u001b[0;36mget\u001b[0;34m(url, params, **kwargs)\u001b[0m\n\u001b[1;32m 70\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 71\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msetdefault\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'allow_redirects'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 72\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mrequest\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'get'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 73\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 74\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/requests/api.py\u001b[0m in \u001b[0;36mrequest\u001b[0;34m(method, url, **kwargs)\u001b[0m\n\u001b[1;32m 56\u001b[0m \u001b[0;31m# cases, and look like a memory leak in others.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 57\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0msessions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSession\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0msession\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 58\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0msession\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 59\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 60\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/requests/sessions.py\u001b[0m in \u001b[0;36mrequest\u001b[0;34m(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)\u001b[0m\n\u001b[1;32m 506\u001b[0m }\n\u001b[1;32m 507\u001b[0m \u001b[0msend_kwargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msettings\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 508\u001b[0;31m \u001b[0mresp\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mprep\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0msend_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 509\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 510\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mresp\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/requests/sessions.py\u001b[0m in \u001b[0;36msend\u001b[0;34m(self, request, **kwargs)\u001b[0m\n\u001b[1;32m 616\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 617\u001b[0m \u001b[0;31m# Send the request\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 618\u001b[0;31m \u001b[0mr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0madapter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 619\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 620\u001b[0m \u001b[0;31m# Total elapsed time of the request (approximately)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/requests/adapters.py\u001b[0m in \u001b[0;36msend\u001b[0;34m(self, request, stream, timeout, verify, cert, proxies)\u001b[0m\n\u001b[1;32m 438\u001b[0m \u001b[0mdecode_content\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 439\u001b[0m \u001b[0mretries\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmax_retries\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 440\u001b[0;31m \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 441\u001b[0m )\n\u001b[1;32m 442\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/urllib3/connectionpool.py\u001b[0m in \u001b[0;36murlopen\u001b[0;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)\u001b[0m\n\u001b[1;32m 599\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtimeout_obj\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 600\u001b[0m \u001b[0mbody\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbody\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mheaders\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 601\u001b[0;31m chunked=chunked)\n\u001b[0m\u001b[1;32m 602\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 603\u001b[0m \u001b[0;31m# If we're going to release the connection in ``finally:``, then\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/urllib3/connectionpool.py\u001b[0m in \u001b[0;36m_make_request\u001b[0;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[1;32m 344\u001b[0m \u001b[0;31m# Trigger any extra validation we need to do.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 345\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 346\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_validate_conn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconn\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 347\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mSocketTimeout\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mBaseSSLError\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 348\u001b[0m \u001b[0;31m# Py2 raises this as a BaseSSLError, Py3 raises it as socket timeout.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/urllib3/connectionpool.py\u001b[0m in \u001b[0;36m_validate_conn\u001b[0;34m(self, conn)\u001b[0m\n\u001b[1;32m 848\u001b[0m \u001b[0;31m# Force connect early to allow us to validate the connection.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 849\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'sock'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;31m# AppEngine might not have `.sock`\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 850\u001b[0;31m \u001b[0mconn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconnect\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 851\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 852\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mconn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mis_verified\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/urllib3/connection.py\u001b[0m in \u001b[0;36mconnect\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 282\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mconnect\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 283\u001b[0m \u001b[0;31m# Add certificate verification\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 284\u001b[0;31m \u001b[0mconn\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_new_conn\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 285\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 286\u001b[0m \u001b[0mhostname\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhost\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/urllib3/connection.py\u001b[0m in \u001b[0;36m_new_conn\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 139\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 140\u001b[0m conn = connection.create_connection(\n\u001b[0;32m--> 141\u001b[0;31m (self.host, self.port), self.timeout, **extra_kw)\n\u001b[0m\u001b[1;32m 142\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 143\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mSocketTimeout\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/urllib3/util/connection.py\u001b[0m in \u001b[0;36mcreate_connection\u001b[0;34m(address, timeout, source_address, socket_options)\u001b[0m\n\u001b[1;32m 58\u001b[0m \u001b[0mfamily\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mallowed_gai_family\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 59\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 60\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0mres\u001b[0m \u001b[0;32min\u001b[0m \u001b[0msocket\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetaddrinfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhost\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mport\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfamily\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msocket\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSOCK_STREAM\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 61\u001b[0m \u001b[0maf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msocktype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mproto\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcanonname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msa\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mres\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 62\u001b[0m \u001b[0msock\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/lib/python3.6/socket.py\u001b[0m in \u001b[0;36mgetaddrinfo\u001b[0;34m(host, port, family, type, proto, flags)\u001b[0m\n\u001b[1;32m 743\u001b[0m \u001b[0;31m# and socket type values to enum constants.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 744\u001b[0m \u001b[0maddrlist\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--> 745\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0mres\u001b[0m \u001b[0;32min\u001b[0m \u001b[0m_socket\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetaddrinfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhost\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mport\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfamily\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mproto\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mflags\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 746\u001b[0m \u001b[0maf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msocktype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mproto\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcanonname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msa\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mres\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 747\u001b[0m addrlist.append((_intenum_converter(af, AddressFamily),\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"person_network(\"Desaparecidos México\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"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": "3.6.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment