From e6a14ba84d5295d0853ea7989e0c0410f279d4a2 Mon Sep 17 00:00:00 2001 From: Tykayn Date: Tue, 22 Oct 2024 00:26:28 +0200 Subject: [PATCH] gynandco output json and csv --- etalab_data/gynadco/gynandco.csv | 71 +++++++++++++++++++++++++++++++ etalab_data/gynadco/gynandco.json | 4 +- etalab_data/gynadco/scrap.py | 19 ++++++--- 3 files changed, 85 insertions(+), 9 deletions(-) create mode 100644 etalab_data/gynadco/gynandco.csv diff --git a/etalab_data/gynadco/gynandco.csv b/etalab_data/gynadco/gynandco.csv new file mode 100644 index 0000000..8616e61 --- /dev/null +++ b/etalab_data/gynadco/gynandco.csv @@ -0,0 +1,71 @@ +name,address,address:code_postal,ref:FR:convention_secteur,contact:phone,contact:website,gender,visioconference_meeting,handles:gender:trans,handles:violence,handles:premenstrual_syndrome,handles:IST,accessible_cabinet,pseudo_science,speaks,handles:tatoo,handles:toxico,handles:sterilisation,handles:abortion,handles:endometriosis,handles:hairy,handles:bigbody,handles:gender:bi,handles:diu,handles:mycoses,handles:pregnancy,handles:auto_prelevement,handles:pma,handles:dyspareunie,handles:gender:lesbian,healcare:generaliste,healcare:sage_femme,healcare:gynecologist +Valérie BARTKOWIAK,"43 rue Laennec, 29490 GUIPAVAS",29490,2,0603234834,https://gynandco.wordpress.com/2024/10/18/valerie-bartkowiak/,unknown,yes,,,,yes,,,french;english,yes,,,,,,,,,,,,,,,,yes, +Alison RICHARD,"142 route de Darnétal, 76000 Rouen",76000,1,,https://gynandco.wordpress.com/2024/10/18/alison-richard/,unknown,yes,,yes,,yes,,,,yes,,,,,,,,yes,,,,,,,,yes, +Anne-Claire DESSE,"110 Bd Michelet, 44000 Nantes (Service de Santé des Etudiants)",44000,1,,https://gynandco.wordpress.com/2024/10/18/anne-claire-desse/,unknown,yes,,yes,,,,,,,,,,,,,,,,,,,yes,,,yes, +Charline DIDIER,"7 Rue de Bourgogne, 69009 Lyon",69009,1,0981358948,https://gynandco.wordpress.com/2024/10/18/charline-didier/,unknown,yes,,yes,,yes,,,,,,,,,,,,,,,yes,,,,,yes, +Pierre DE TROGOFF,"103 avenue de la République, 75011 Paris",75011,1,,https://gynandco.wordpress.com/2024/10/18/pierre-de-trogoff/,unknown,yes,yes,yes,,yes,,,french;english,,,,,,,,,yes,,,yes,,,,,yes, +Philippe DESSARD,"6 Boulevard de la Boutière, 35760 Saint-Grégoire",35760,2,,https://gynandco.wordpress.com/2024/10/18/philippe-dessard/,unknown,yes,,,,,,,,,,,,,,,,,,yes,,yes,,yes,,,yes +Céline DELPOUVE PARCOIT,"150 rue Verlyck, 59190 Hazebrouck",59190,1,0678604740,https://gynandco.wordpress.com/2024/10/18/celine-delpouve-parcoit/,unknown,yes,,,,,,,,,,,,,,,,yes,,,,,,,,yes, +Gaëlle PERRILLAT BOITEUX,"5 route des Besseaux, 74230 Thônes",74230,1,0768510762,https://gynandco.wordpress.com/2024/10/15/gaelle-perrillat-boiteux/,unknown,yes,,,,,,,french;english;spanish,,,,,,,,,,,yes,,,,,,yes, +Eléonore BELINKI,"Cabinet des Canuts, 32 Rue Valentin Couturier, 69004 Lyon",69004,1,,https://gynandco.wordpress.com/2024/10/15/eleonore-belinki/,unknown,yes,,yes,,,,,,,,,yes,,,,,yes,,,,,,,,yes, +Louis LECARME,"166 avenue de Castres, 31500 Toulouse",31500,1,,https://gynandco.wordpress.com/2024/10/15/louis-lecarme/,unknown,yes,,yes,,yes,,,,,,yes,,,,,,,,,,,,,yes,, +Emilie RACHET,"Cabinet de la Tour, 2 rue des fossés, 78 550 Houdan",,1,0973032166,https://gynandco.wordpress.com/2024/10/15/emilie-rachet/,unknown,yes,,,,,,,,,,,,,yes,,,yes,,,,,,,,yes, +Mathieu HENNON,"1 rue Roger Salengro, 62410 Hulluch",62410,1,0374855788,https://gynandco.wordpress.com/2024/10/15/mathieu-hennon/,unknown,no,,,,,,,,,,,,,,,yes,,,,,,,,yes,, +Jean-Sébastien CADWALLER,"5 Rue du Docteur Pesqué, 93300 Aubervilliers",93300,1,0148112190,https://gynandco.wordpress.com/2024/10/15/jean-sebastien-cadwaller/,unknown,yes,,yes,,,,,french;english,,,yes,,,,,,yes,,,,,,,yes,, +Laura MARTIN,"4 rue du four brûlée, 37110 Château Renault",37110,1,,https://gynandco.wordpress.com/2024/10/13/laura-martin/,unknown,yes,,yes,,yes,,,,,,,yes,,,,,yes,,,yes,,,,,yes, +Mariette DUTILLEUL,"26 allée de la Glanerie, 59890 Quesnoy-sur-Deûle",59890,1,0674677181,https://gynandco.wordpress.com/2024/10/12/mariette-dutilleul/,unknown,yes,,,,,,,,,,,,,,,,,,,,yes,,,,yes, +Marielle CODBESSIN,"3 rue du tertre vert, 22190 Plérin",22190,1,0296745848,https://gynandco.wordpress.com/2024/10/12/marielle-codbessin/,unknown,no,,yes,,,,,,,,,,,,,,yes,,,,,,,,yes, +Sophie BEUZART,"33 Rue Emile Rousse, 29200 Brest",29200,1,,https://gynandco.wordpress.com/2024/10/12/sophie-beuzart/,unknown,yes,,yes,,yes,,,,,,,,,,,,yes,,,,,,,,yes, +Catherine DUTHOY,"Allée Philippe Polderman, 31400 Toulouse",31400,1,0661862095,https://gynandco.wordpress.com/2024/10/12/catherine-duthoy/,unknown,yes,,yes,,yes,,,,,,,,,,,,yes,,,yes,,yes,,,yes, +Marie MORIN,"842 Rue de l’Amiral, 50200 Tourville-sur-Sienne",50200,1,0777787128,https://gynandco.wordpress.com/2024/10/12/marie-morin/,unknown,yes,,,,yes,,yes,french;english,,,,,,,,,yes,,,yes,,,,,yes, +Odile WANDJI,"8 Rue de Maillé, 91310 Montlhéry",91310,2,,https://gynandco.wordpress.com/2024/10/12/odile-wandji/,unknown,yes,,yes,,,,,french;english,,,,yes,,,,,yes,,,,,,,,,yes +Catherine MURIS,"2 Place Pierre et Marie Curie, 14200 Hérouville Saint Clair",14200,1,0231068818,https://gynandco.wordpress.com/2024/10/11/catherine-muris/,unknown,yes,,yes,,,,,,,,,,,,,,,,,yes,yes,,,,,yes +Aurore GUIER,"30 Av. Paul-Emile Victor, 98830 Dumbéa, Nouvelle-Calédonie",98830,1,,https://gynandco.wordpress.com/2024/10/11/aurore-guier/,unknown,no,,,,,,,,,,,,,,,,yes,,yes,,,,,,yes, +Chloé POULAIN,"Espace médicale du faubourg, 111 Rue de Nivelle, 59230 Saint-Amand-les-Eaux",59230,2,0327406072,https://gynandco.wordpress.com/2024/10/11/chloe-poulain/,unknown,no,,yes,,,,,,,,,yes,,,,,,,,,,,,,,yes +Benjamin PORTE CAZAUX,"2 Route du Baqué, 31390 Carbonne",31390,1,0561909160,https://gynandco.wordpress.com/2024/10/11/benjamin-porte-cazaux/,unknown,yes,,yes,,,,,,,,yes,,,,,,yes,,,,,,,yes,, +Alexandra LASCOMBE,"12 Avenue Lieutenant Cheynis, 26160 La Bâtie-Rolland",26160,1,0685227396,https://gynandco.wordpress.com/2024/10/08/alexandra-lascombe/,unknown,yes,,yes,,yes,,,,yes,,,,,,,,yes,yes,,yes,,,,,yes, +Elodie GINESTE,"12 rue Jean Jaures, 81290 Labruguière",81290,1,0788121758,https://gynandco.wordpress.com/2024/10/08/elodie-gineste/,unknown,yes,,,,,,,,,,,,,,,,,,yes,,,,,,yes, +Fabienne MALLERET,22 avenue Georges Gershwin 63200 Riom,63200,1,0473643978,https://gynandco.wordpress.com/2024/10/08/fabienne-malleret/,unknown,yes,,yes,,,,,,,,,,,,,,,,,,,yes,,,yes, +Stéphanie BARBIER,"Rue Alfred Thillard, 76620 Le Havre",76620,1,0235464750,https://gynandco.wordpress.com/2024/10/08/stephanie-barbier/,unknown,yes,,yes,,yes,,,,,,,,,yes,,,yes,,,yes,,,,,yes, +Bleuenn RIDARD,"24 rue du Commerce, 81100 Castres",81100,1,0778434800,https://gynandco.wordpress.com/2024/10/08/bleuenn-ridard/,unknown,no,yes,yes,,yes,,,,,,,,,,,,,,,yes,,,,,yes, +Emma WURSTEN,"18b Rue Jules Ferry, 13220 Châteauneuf-les-martigues",13220,1,0621695768,https://gynandco.wordpress.com/2024/10/08/emma-wursten/,unknown,yes,,yes,,yes,,,,,,,yes,,,,,yes,,,,,,,,yes, +Morgane POIGNET,"12 ZA la Burliere, 13530 TRETS",13530,1,0632930496,https://gynandco.wordpress.com/2024/10/01/morgane-poignet/,unknown,yes,,yes,,yes,,,,,,yes,yes,,,,,yes,,yes,yes,,,,,yes, +Marie FERRIERES,100 chemin des romains 34560 MONTBAZIN,34560,1,0467789097,https://gynandco.wordpress.com/2024/10/01/marie-ferrieres/,unknown,yes,,yes,,yes,,,french;english;spanish,,,yes,yes,,,,,yes,,yes,yes,,,,,yes, +Marine DEBORT,"153 Avenue de Fronton, 31200 Toulouse",31200,1,,https://gynandco.wordpress.com/2024/10/01/marine-debort/,unknown,yes,,,,yes,,,,,,,,,,,,,,,,,,,,yes, +Marie DURAND SEZNEC,"13 avenue de la gare, 44130 BLAIN",44130,1,0240799610,https://gynandco.wordpress.com/2024/10/01/marie-durand-seznec/,unknown,no,,,,yes,,,,yes,,,,,yes,,,yes,,,yes,,,,,yes, +Patricia RAVASY,"Maison médicale Saint-Nicolas 2 rue Saint-Nicolas, 77950 Rubelles",77950,1,0603525766,https://gynandco.wordpress.com/2024/10/01/patricia-ravasy/,unknown,yes,,yes,,,,,,,,,,,,,,yes,,yes,,,,,,yes, +Alexie GAUTHIER,"2 Rue des Fiefs, L’Aiguillon-sur-Vie, 85220",85220,1,,https://gynandco.wordpress.com/2024/10/01/alexie-gauthier/,unknown,yes,,yes,,yes,,yes,,,,,,,,,,yes,,,yes,,,,,yes, +Colin GALLICE,"Centre médical Ambroise Paré, boulevard Ambroise Paré, 69008 Lyon",69008,2,,https://gynandco.wordpress.com/2024/10/01/colin-gallice/,unknown,yes,,yes,yes,,,yes,,,,,,,,,,yes,,,,,,,,,yes +Marie Meghan CARTIAUX,"29 Chemin du Pioch de Gaïx, 81090 Castres",81090,2,,https://gynandco.wordpress.com/2024/10/01/marie-meghan-cartiaux/,unknown,no,,,,yes,,,,yes,,,,,,,,,,,yes,,,,,yes, +Coralie BOREL,"Maison de santé des Monts d’Arrée, 58 rue de Brest, 29450 Sizun",29450,1,,https://gynandco.wordpress.com/2024/10/01/coralie-borel/,unknown,yes,,,,,,,french;english,,,yes,,,,,,,,,yes,,yes,,,yes, +Julia COUFFIN,"20 rue de la République, 12100 Millau",12100,1,0638025086,https://gynandco.wordpress.com/2024/10/01/julia-couffin/,unknown,no,,,,yes,,,,,,,,,,,,yes,,,yes,,,,,yes, +Elsa MARIN,"Centre hospitalier de Sallanches, 380 rue de l’hôpital, 74700 Sallanches",74700,,0457272045,https://gynandco.wordpress.com/2024/10/01/elsa-marin/,unknown,no,,,,yes,,,,,,,yes,,,,,yes,,,yes,,,,yes,, +Orlanne POLIZZI,"6 Rue des Rosiers, 38300 BOURGOIN JALLIEU",38300,1,0474433646,https://gynandco.wordpress.com/2024/09/19/orlanne-polizzi/,unknown,yes,,yes,,yes,,,,,,,,,,,,yes,,,,,,,,yes, +Dyhia MOUSSAOUI,"Centre Hospitalier Intercommunal Alençon-Mamers, 25 Rue de Fresnay, 61000 Alençon",61000,1,0233323030,https://gynandco.wordpress.com/2024/09/17/dyhia-moussaoui/,unknown,no,,,,yes,,,,,,,,,,,,yes,,,,,,,,,yes +Mélissa AMAYA,"29 Boulevard François Suarez, 06340 La Trinité",06340,1,0667572730,https://gynandco.wordpress.com/2024/09/17/melissa-amaya/,unknown,yes,,yes,,,,,french;english;spanish,,,,,,,,,,,,,,,,,yes, +Huda POSTIC,16 rue des Genêts 29252 Plouezoc’h,29252,1,0664796398,https://gynandco.wordpress.com/2024/09/17/huda-postic/,unknown,yes,,,,,,,,,,,,,,,,,,,,,,,,yes, +Alexandra SASPORTAS,"8 Boulevard de Magenta, 75010 Paris",75010,1,,https://gynandco.wordpress.com/2024/09/17/alexandra-sasportas/,unknown,yes,,yes,,yes,,,,,,,,,,,,yes,,,yes,,,,,yes, +Anne ALFASSA,70 FISMES,,1,0326480252,https://gynandco.wordpress.com/2024/09/17/anne-alfassa/,unknown,yes,,,,yes,,yes,,,,,,,,,,,,,,,,,yes,, +Isabelle WEIBEL,13 rue du dragon 57450 Farebersviller,57450,1,0681125615,https://gynandco.wordpress.com/2024/09/17/isabelle-weibel/,unknown,no,,,,,,,,,,,,,,,,yes,,yes,,,,,,yes, +Pauline CONGRATEL,"7 rue Leclerc, 35140 St Aubin du Cormier",35140,1,0659151823,https://gynandco.wordpress.com/2024/09/17/pauline-congratel/,unknown,yes,,yes,,,,,,,,,,,,,,,,yes,,,,,,yes, +Svenja DELACOUR,"5 rue de la Chalotais, 35510 Cesson-Sévigné",35510,,0299831336,https://gynandco.wordpress.com/2024/09/17/svenja-delacour/,unknown,yes,,yes,,,,,french;english,,,,yes,,,,,yes,,yes,,,,,,yes, +Anaïs DAUVERGNE,"35 Rue de la Soie, 69100 Villeurbanne",69100,,0478938968,https://gynandco.wordpress.com/2024/09/17/anais-dauvergne/,unknown,yes,,,,,,,,,,,,,,,,,,,,yes,,,,,yes +Bertrand MAY,"37 rue Julie Daubié, 54000 Nancy",54000,2,0383951191,https://gynandco.wordpress.com/2024/09/16/bertrand-may/,unknown,yes,,,,yes,,,,,,yes,,,,,,yes,,,,,,,,,yes +Julie BRICHON,"Pôle Médical Gambetta, 11 Rue Gambetta, 33290 Blanquefort",33290,1,0556571646,https://gynandco.wordpress.com/2024/09/16/julie-brichon/,unknown,yes,,,,yes,,,,yes,,,,,,,,yes,,,yes,,,,,yes, +Calistine ROUANET,"45 rue Sadi Carnot, 59113 Seclin",59113,,0768861502,https://gynandco.wordpress.com/2024/09/16/calistine-rouanet/,unknown,yes,,yes,,yes,,,,,,,yes,,yes,,,yes,,,yes,,,,,yes, +Marianne LAINE,"13 Rue Herbière, 76000 Rouen",76000,1,0235988082,https://gynandco.wordpress.com/2024/09/16/marianne-laine/,unknown,yes,,,,,,,,,,,,,,,,yes,,,,,,,yes,, +Mathilde EMARD-BURRIAT,"Cabinet Gynecologia, 75 Avenue Gabriel Péri, 38400 Saint-Martin-d’Hères",38400,1,,https://gynandco.wordpress.com/2024/09/16/mathilde-emard-burriat/,unknown,yes,,,,yes,,,,,,,,,,,,,,,,yes,,,,,yes +Marine VIGIE,"Institut de médecine Cassis, 7 chemin du mont Gibaou, Les coteaux du Brégadan, 13260 Cassis",13260,1,0624312876,https://gynandco.wordpress.com/2024/09/16/marine-vigie/,unknown,yes,,,,,,,french;english,,,,,,yes,,,,,,,,,,,yes, +Marie-Laure TITIMAL-CANDELLE,"34 Rue François Carlier, 62530 Hersin-Coupigny",62530,1,0663962030,https://gynandco.wordpress.com/2024/08/12/marie-laure-titimal-candelle/,unknown,yes,,,,yes,,,,,,,,,yes,,,yes,,,yes,,,,,yes, +Coralie GRAND,"532 Chemin des Noyers, 38530 CHAPAREILLAN",38530,1,0954658656,https://gynandco.wordpress.com/2024/08/12/coralie-grand/,unknown,yes,,,,,,,,yes,,yes,,,,,,yes,,yes,yes,,,,,yes, +Antoine DRAIN,"La Brigantine Résidence de l’ile aux bois, 1 All. Carolus, 59000 Lille",59000,1,0320092434,https://gynandco.wordpress.com/2024/08/12/antoine-drain/,unknown,yes,,,,,,,,,,yes,,,,,,,,,,,,,,,yes +Christina LONGO,"9 bis Av. du Maréchal Foch, 06190 Roquebrune-Cap-Martin",06190,1,0412101211,https://gynandco.wordpress.com/2024/08/12/christina-longo/,unknown,yes,,,,,,,french;english,yes,,yes,,,yes,,yes,,,,,,,,,,yes +Alicia FERNANDES HERRAULT,"10 Rue du Manet, 74130 Bonneville",74130,1,0688455531,https://gynandco.wordpress.com/2024/08/12/alicia-fernandes-herrault/,unknown,yes,,yes,,yes,,,,,,,,,yes,,,,,,yes,,,,,yes, +Jonathan COHEN-SCALI,"4 rue Jules Grevy, 34000 Montpellier",34000,1,0467725825,https://gynandco.wordpress.com/2024/08/12/jonathan-cohen-scali/,unknown,no,,,,,,,french;english,,,,,,,,,yes,,,yes,,,,yes,, +Malika ROMANO,"CPEF Centre de planification et d’éducation familial, 5 bis rue Devosge, 21000 DIJON",21000,1,0380636834,https://gynandco.wordpress.com/2024/08/12/malika-romano/,unknown,no,yes,yes,,,,,french;english,,,yes,yes,,,,,yes,,yes,,,,,yes,, +Ismahan BADACHE,"154 Avenue Jules Cantini, 13008, Marseille",13008,1,0491407863,https://gynandco.wordpress.com/2024/08/12/ismahan-badache/,unknown,yes,,yes,,yes,,,,,,,yes,,,,,yes,,,yes,,,,,yes, +Inès SAMAD,Place Saint Michel – 33192 La Réole,33192,1,,https://gynandco.wordpress.com/2024/08/12/ines-samad/,unknown,no,,,,,,,,,,yes,yes,,,,,yes,,,,,,,,,yes +Aurore VERHOEVEN,"6 place Jacqueline et Jean Lerat, 18000 Bourges",18000,1,0248700301,https://gynandco.wordpress.com/2024/08/12/aurore-verhoeven/,unknown,yes,,,,yes,,,,,,,,,,,,,,,,,,,,yes, +Julien ARTIGNY,"70 chemin de Baluffet, 31300 Toulouse",31300,1,0561404595,https://gynandco.wordpress.com/2024/08/12/julien-artigny/,unknown,yes,,yes,,,,,french;english,,,,,,,,,,,,,,,,yes,, +Sandrine WILLIAMSON,"46 rue du montaigu, 53600 Evron",53600,1,0626632039,https://gynandco.wordpress.com/2024/08/12/sandrine-williamson/,unknown,yes,,yes,,,,,,,,,,,,,,yes,,yes,,,,,,yes, +Périnne GODEFROY,"415 avenue Colonel Pechot, 54200 Toul",54200,1,0383627059,https://gynandco.wordpress.com/2024/08/12/perinne-godefroy/,unknown,yes,,,,,,,,,,,,,,,,yes,,yes,yes,,,,,yes, diff --git a/etalab_data/gynadco/gynandco.json b/etalab_data/gynadco/gynandco.json index f035f7a..9acf983 100644 --- a/etalab_data/gynadco/gynandco.json +++ b/etalab_data/gynadco/gynandco.json @@ -1099,7 +1099,7 @@ "handles:IST": "yes", "accessible_cabinet": "", "pseudo_science": "", - "speaks": ";spanish", + "speaks": "french;english;spanish", "handles:tatoo": "", "handles:toxico": "", "handles:sterilisation": "yes", @@ -1519,7 +1519,7 @@ "handles:IST": "", "accessible_cabinet": "", "pseudo_science": "", - "speaks": ";spanish", + "speaks": "french;english;spanish", "handles:tatoo": "", "handles:toxico": "", "handles:sterilisation": "", diff --git a/etalab_data/gynadco/scrap.py b/etalab_data/gynadco/scrap.py index 5f0c50f..a8ec0e9 100644 --- a/etalab_data/gynadco/scrap.py +++ b/etalab_data/gynadco/scrap.py @@ -3,7 +3,7 @@ import geopandas as gpd from bs4 import BeautifulSoup from shapely.geometry import Point import re - +import pandas as pd def extraire_numero_telephone(line): # Extraction des nombres dans la ligne @@ -11,7 +11,7 @@ def extraire_numero_telephone(line): if numbers: numbers = ''.join(numbers) - print('numbers',numbers) +# print('numbers',numbers) # Vérification si un numéro de téléphone est présent if len(numbers) == 10: # Reconstruction du numéro de téléphone @@ -35,7 +35,7 @@ def extraire_addr_line(line): numbers = re.findall(r'\d+', line) # Vérification si un numéro de téléphone est présent - if len(numbers) == 2 and ',' in line: + if len(numbers) == 2 and ',' in line and len(numbers[1]) == 5: return line else: return None @@ -65,7 +65,7 @@ for article in articles: em = article.find("em") if em: address = em.text - print(address) +# print(address) # Vérifier si le contenu de l'article contient "Secteur 1" if "Secteur 1" in article.text: @@ -116,7 +116,7 @@ for article in articles: address = line found = extraire_numero_telephone(line) if found: - print(found) +# print(found) phone_number = found if 'Rdv en ligne possible' in line: visio_meeting = 'yes' @@ -167,7 +167,7 @@ for article in articles: if 'français, anglais' in line: spoken = 'french;english' if 'espagnol' in line: - spoken = (spoken+';spanish') + spoken = ('french;english;spanish') if 'Dyspareunie' in line: dyspareunie = 'yes' if 'Gynécologue' in line: @@ -176,7 +176,7 @@ for article in articles: if not address: found = extraire_addr_line(line) if found: - print(found) +# print(found) address = found @@ -224,3 +224,8 @@ for article in articles: # Enregistrer les informations des docteurs au format JSON dans un fichier with open("gynandco.json", "w", encoding="utf-8") as f: json.dump(doctors, f, ensure_ascii=False, indent=2) + +with open('gynandco.json', 'r') as f: + data = json.load(f) +df = pd.DataFrame(data) +df.to_csv('gynandco.csv', index=False)