fork download
copy 
  1. import requests
  2. from bs4 import BeautifulSoup
  3. import pandas as pd
  4. import os
  5. import re
  6. import csv
  7. from math import *
  8.  
  9. def build_url(i, num_page):
  10.     try:
  11.         if (i == '2A' or i == '2B'):
  12.             url = 'https://w...content-available-to-author-only...v.fr/annuaire-ehpad-en-hebergement-permanent/{0}/0?page={1}'.format(i, num_page)
  13.         elif (i < 10):
  14.             url = 'https://w...content-available-to-author-only...v.fr/annuaire-ehpad-en-hebergement-permanent/0{0}/0?page={1}'.format(i, num_page)
  15.         else:
  16.             url = 'https://w...content-available-to-author-only...v.fr/annuaire-ehpad-en-hebergement-permanent/{0}/0?page={1}'.format(i, num_page)
  17.         return(url)
  18.     except:
  19.         return None
  20.  
  21. def find_nb_results(url):
  22.     try:
  23.         headers = {"User-Agent":"Mozilla/5.0"}
  24.         response = requests.get(url, headers=headers, timeout=5)
  25.         soup = bs4.BeautifulSoup(response.text, 'lxml')
  26.         target = (soup.find('h2', {'id': "cnsa-search-total-phone"}).text)
  27.         target = ''.join(c for c in target if c.isdigit())  
  28.         return(target)
  29.     except:
  30.         return None
  31.  
  32. def find_ehpad(url, nb):
  33.     try:
  34.         headers = {"User-Agent":"Mozilla/5.0"}
  35.         response = requests.get(url, headers=headers, timeout=5)
  36.         soup = bs4.BeautifulSoup(response.text, 'lxml')
  37.         target = (soup.findAll('div', {'class': "cnsa_results-item-inside"})[nb])
  38.         name = target.find('h3', {'class': "cnsa_results-tags1"}).text
  39.         price = target.find('div', {'class': "clearfix"}).find('div', {'class': "prix"}).find('strong').text
  40.         return(name, price)
  41.     except:
  42.         # Gère le cas des EHPAD qui ne mentionnent pas le prix requis pour un hébergement en chambre seule
  43.         headers = {"User-Agent":"Mozilla/5.0"}
  44.         response = requests.get(url, headers=headers, timeout=5)
  45.         soup = bs4.BeautifulSoup(response.text, 'lxml')
  46.         target = (soup.findAll('div', {'class': "cnsa_results-item-inside"})[nb])
  47.         name = target.find('h3', {'class': "cnsa_results-tags1"}).text
  48.         return (name, 'non indiqué')
  49.  
  50. def find_results(i):
  51.     ct = 0
  52.     url = build_url(i, 0)
  53.     nb_results = int(find_nb_results(url))
  54.     nb_page_by_dep = ceil(nb_results/10) - 1
  55.     while (ct <= nb_page_by_dep):
  56.         div = 0
  57.         url_in_progress = build_url(i, ct)
  58.         ct = ct + 1
  59.         if (ct < nb_page_by_dep): 
  60.             while(div < 10):
  61.                 name, price = find_ehpad(url_in_progress, div)
  62.                 div = div + 1
  63.         else:
  64.             total_div = nb_results - nb_page_by_dep * 10
  65.             while(div < total_div):
  66.                 name, price = find_ehpad(url_in_progress, div)
  67.                 div = div + 1
  68.  
  69.     # Recherche des résultats pour les départements de France métropolitaine
  70. i = 1
  71. while (i <= 95):
  72.     find_results(i)
  73.     print(i)
  74.     i = i + 1
  75.     break
  76. # Recherche des résultats pour les départements d'Outre-Mer.
  77. i = 971
  78. while (i <= 976):
  79.     find_results(i)
  80.     print(i)
  81.     i = i + 1
  82. # Recherche des résultats pour la Corse
  83. find_results('2A')
  84. find_results('2B')
  85.  
Runtime error #stdin #stdout #stderr 0.33s 34236KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
Standard output is empty
stderr
copy 
Traceback (most recent call last):
  File "./prog.py", line 2, in <module>
ModuleNotFoundError: No module named 'bs4'
https://ideone.com/G2blLl
language:
Python 3 (python  3.9.5)
created:
4 years ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!