Hello,
Still working on my plan to migrate from Jeedom to Home Assistant, I have a couple of things left to do, including this:
Retrieving information from a website using the Scrape integrator.
The website is Horoscoop, Rachel’s Horoscope - Radio SCOOP
Here is the configuration that does not work.
Pics of like
Text
Can you help me? Thank you
I’ve tried several things but nothing is working. Can you help me?
Thanks in advance.
- sensor:
- name: "Horoscope Debug HTML"
state: >-
{% set content = state_attr('sensor.horoscope_raw_data', 'content') %}
{{ content[0:200] }} # Affiche les 200 premiers caractères
# --- Compteurs d'icônes ---
- name: "Horoscope Amour (Icônes)"
unit_of_measurement: "❤️"
state: >-
{% set content = state_attr('sensor.horoscope_raw_data', 'content') %}
{{ content.split('horo_amour.png').length - 1 if content else 0 }}
- name: "Horoscope Santé (Icônes)"
unit_of_measurement: "💪"
state: >-
{% set content = state_attr('sensor.horoscope_raw_data', 'content') %}
{{ content.split('horo_sante.png').length - 1 if content else 0 }}
- name: "Horoscope Travail (Icônes)"
unit_of_measurement: "💼"
state: >-
{% set content = state_attr('sensor.horoscope_raw_data', 'content') %}
{{ content.split('horo_travail.png').length - 1 if content else 0 }}
# --- Texte principal ---
- name: "Horoscope Texte Principal"
state: >-
{% set content = state_attr('sensor.horoscope_raw_data', 'content') %}
{% if content %}
{% set start = content.find('horo_travail.png') + 15 %}
{% set end = content.find('Tirage Belline') %}
{% if start != -1 and end != -1 %}
{{ content[start:end] | replace('<br>', ' ') | replace('\n', ' ') | trim }}
{% else %}
"Texte non disponible"
{% endif %}
{% else %}
"Chargement..."
{% endif %}
# --- Tirage Belline ---
- name: "Horoscope Tirage Belline"
state: >-
{% set content = state_attr('sensor.horoscope_raw_data', 'content') %}
{% if content %}
{% set start = content.find('Tirage Belline') + 14 %}
{% set end = content.find('RACHEL CONSEILS') %}
{% if start != -1 and end != -1 %}
{{ content[start:end] | replace('<br>', ' ') | replace('\n', ' ') | trim }}
{% else %}
"Tirage non disponible"
{% endif %}
{% else %}
"Chargement..."
{% endif %}
# Début Horoscope ----------------------------------------------------------
rest:
- resource: "https://www.radioscoop.com/horoscoop.php?id=19"
scan_interval: 3600
headers:
User-Agent: "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
Accept: "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"
Accept-Language: "fr-FR,fr;q=0.9,en-US;q=0.8,en;q=0.7"
sensor:
- name: "Horoscope Raw Data"
value_template: "OK"
json_attributes_path: "$"
# Fin Horoscope ----------------------------------------------------------
multiscrape:
- name: radioscoop_horoscope
resource: "https://www.radioscoop.com/horoscoop.php?id=19" # ID 19 = Sagittaire (à adapter)
scan_interval: 3600 # Met à jour toutes les heures
sensor:
- unique_id: horoscope_sagittaire # Identifiant unique pour Home Assistant
name: "Horoscope Sagittaire" # Nom du sensor
select: "#hJour9" # Sélecteur CSS pour extraire l'horoscope
value_template: "{{ value | regex_replace('<[^>]*>', '') | trim }}" # Nettoie le HTML
attributes: # (Optionnel) Pour extraire d'autres infos si besoin
- name: "amour"
select: ".amour" # Exemple : si tu veux extraire une section "Amour"
multiscrape:
- name: radioscoop_horoscope
resource: "https://www.radioscoop.com/horoscoop.php?id=19"
scan_interval: 3600
headers:
User-Agent: "Mozilla/5.0"
sensor:
- unique_id: horoscope_sagittaire
name: "Horoscope Sagittaire"
select: "#hJour9"
value_template: >-
{% set raw_text = value %}
{% set clean_text = raw_text.split('Tirage de cauris')[0] | trim %}
{% set parts = clean_text.split('Travail') %}
{% set travail = parts[1] | regex_replace('[\n\s]+', ' ') | trim %}
{% set parts = parts[0].split('Santé') %}
{% set sante = parts[1] | regex_replace('[\n\s]+', ' ') | trim %}
{% set parts = parts[0].split('Amour') %}
{% set amour = parts[1] | regex_replace('[\n\s]+', ' ') | trim %}
{{ (amour + " " + sante + " " + travail) | trim | truncate(255) }}
attributes:
- name: "amour"
value_template: >-
{% set raw_text = value %}
{% set clean_text = raw_text.split('Tirage de cauris')[0] | trim %}
{% set parts = clean_text.split('Amour') %}
{{ parts[1].split('Santé')[0] | regex_replace('[\n\s]+', ' ') | trim }}
- name: "sante"
value_template: >-
{% set raw_text = value %}
{% set clean_text = raw_text.split('Tirage de cauris')[0] | trim %}
{% set parts = clean_text.split('Santé') %}
{{ parts[1].split('Travail')[0] | regex_replace('[\n\s]+', ' ') | trim }}
- name: "travail"
value_template: >-
{% set raw_text = value %}
{% set clean_text = raw_text.split('Tirage de cauris')[0] | trim %}
{% set parts = clean_text.split('Travail') %}
{{ parts[1] | regex_replace('[\n\s]+', ' ') | trim }}
Nailed it
command_line:
- sensor:
name: "Horoscope Sagittaire"
unique_id: horoscope_complet_json
icon: mdi:zodiac-sagittarius
# On remplace <br> par \n\n pour forcer le saut de ligne dans la carte Markdown
command: >
curl -s 'https://www.radioscoop.com/horoscoop.php?id=19' | python3 -c "import sys, re, json; h = sys.stdin.read(); amour = h.count('horo_amour.png'); sante = h.count('horo_sante.png') + h.count('horo_forme.png'); travail = h.count('horo_travail.png'); m = re.search(r'style=\"font-weight:bold ; font-size:20px ; font-style:italic ; padding:10px\">([\s\S]*?)<\/div>', h); t = m.group(1) if m else 'Non disponible'; t = re.sub(r'<br\s*/?>', '\n', t); t = re.sub(r'<[^>]+>', '', t); t = re.sub(r'\n+', '\n', t).strip(); print(json.dumps({'amour': amour, 'sante': sante, 'travail': travail, 'texte': t}));"
value_template: "Mis à jour"
scan_interval: 86400
json_attributes:
- amour
- sante
- travail
- texte
