Last active
June 13, 2019 21:52
-
-
Save rhanka/38ababbed8812e53d823a5c2762abb96 to your computer and use it in GitHub Desktop.
download BRPP INSEE data
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
#!/bin/bash | |
#login et mdp doivent être url encoded (uriComponent et pas simplement uri) | |
set -e | |
set echo off | |
first_year=1970 | |
login=MYBRPPLOGIN | |
password=MYURLENCODEDPASSWORD | |
# étape 1: création d'un jeton de session (stockage dans cookie1) | |
curl -s -c cookie1 https://echanges.insee.fr/ihm/download/brpp-deces -o session.html && echo initialisation de session || echo initialisation de session en échec | |
# étape 2: login => renvoie un autre jeton de session, valant authent (stockage dans cookie2) | |
curl -s -b cookie1 -c cookie2 'https://echanges.insee.fr/ihm/download/brpp-deces' \ | |
-H 'User-Agent: Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:66.0) Gecko/20100101 Firefox/66.0'\ | |
-H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' \ | |
-H 'Accept-Language: fr,fr-FR;q=0.8,en-US;q=0.5,en;q=0.3' \ | |
--compressed -H 'Referer: https://echanges.insee.fr/ihm/download/brpp-deces'\ | |
-H 'Content-Type: application/x-www-form-urlencoded' -H 'DNT: 1' -H 'Connection: keep-alive' \ | |
-H 'Upgrade-Insecure-Requests: 1' -H 'Pragma: no-cache' -H 'Cache-Control: no-cache' \ | |
--data "userContext.aliasOperationId=fourniture+des+fichiers+d%C3%A9c%C3%A8s&userContext.userId=${login}&userContext.password=${password}&action%3AdownloadInit=+++Retirer+des+fichiers+++&userContext.pageOrigine=download&userContext.operationId=brpp-deces"\ | |
-o login.html && echo login || echo login failed | |
# étape 3: récupération des fichiers | |
# commande de listing des fichiers (paginée) | |
curl -s --compressed -b cookie2 https://echanges.insee.fr/ihm/downloadListeFichiers -o test.html && echo login ok | |
# 3.1: récupération des années précédentes | |
last_year=`date --date="1 year ago" +'%Y'` | |
echo récupération des années ${first_year} à ${last_year} | |
for y in `seq ${first_year} ${last_year}`;\ | |
do \ | |
[ ! -f Deces_${y}.txt ] && \ | |
echo "récupération année ${y}" &&\ | |
(curl -s --compressed -b cookie2 "https://echanges.insee.fr/ihm/download_Deces_${y}.txt.html?nomFichier=Deces_${y}.txt" > Deces_${y}.txt) &&\ | |
echo "${y}: ok";\ | |
done | |
# 3.2: récupération des mois précédents | |
last_month=`date --date="1 month ago" +'%m'` | |
y=`date +'%Y'` | |
m=`date --date '1 month ago' +'%m'` | |
echo récupération des mois de l\'année en cours | |
for m in `seq 1 ${m}`;\ | |
do \ | |
m=$(printf %02d $m);\ | |
echo $m;\ | |
[ ! -f Deces_${y}_M${m}.txt ] &&\ | |
echo "récupération année ${y} mois ${m}" &&\ | |
(curl -s --compressed -b cookie2 "https://echanges.insee.fr/ihm/download_Deces_${y}_M${m}.txt.html?nomFichier=Deces_${y}_M${m}.txt" > Deces_${y}_M${m}.txt) &&\ | |
echo "${y}: ok";\ | |
done | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment