diff --git a/aggregators/filmspourenfants-adapter.js b/aggregators/filmspourenfants-adapter.js new file mode 100644 index 0000000..2c1974b --- /dev/null +++ b/aggregators/filmspourenfants-adapter.js @@ -0,0 +1,229 @@ +const axios = require('axios'); +const cheerio = require('cheerio'); +const fs = require('fs'); +const path = require('path'); + +const BASE_URL = 'https://www.filmspourenfants.net'; + +// Setup disk cache +const CACHE_DIR = path.join(__dirname, '../cache'); +if (!fs.existsSync(CACHE_DIR)) fs.mkdirSync(CACHE_DIR, { recursive: true }); + +// Cache operations +function loadCache(type, key) { + try { + const file = path.join(CACHE_DIR, `fpe_${type}_${key.replace(/[^a-z0-9]/gi, '_')}.json`); + if (fs.existsSync(file)) { + const stats = fs.statSync(file); + // Cache valid for 24 hours + if (Date.now() - stats.mtime.getTime() < 86400000) { + return JSON.parse(fs.readFileSync(file, 'utf8')); + } + } + } catch (e) { + console.error('Cache load error:', e.message); + } + return null; +} + +function saveCache(type, key, data) { + try { + const file = path.join(CACHE_DIR, `fpe_${type}_${key.replace(/[^a-z0-9]/gi, '_')}.json`); + fs.writeFileSync(file, JSON.stringify(data)); + } catch (e) { + console.error('Cache save error:', e.message); + } +} + +// Extract age from string like "À partir de 8 ans" or "Déconseillé aux moins de: 8 ans" +function extractAgeFromText(text) { + if (!text) return null; + + const match = text.match(/(\d+)\s*ans/i); + if (match && match[1]) { + return parseInt(match[1]); + } + return null; +} + +async function searchMovies(query) { + // Check cache first + const cached = loadCache('search', query); + if (cached) return cached; + + const searchUrl = `${BASE_URL}/films-resultats/?_s=${encodeURIComponent(query)}`; + console.log('Searching FilmsPourEnfants:', searchUrl); + + try { + const response = await axios.get(searchUrl, { + headers: { 'User-Agent': 'Mozilla/5.0' } + }); + const $ = cheerio.load(response.data); + const results = []; + + $('section.gp-post-item').each((_, el) => { + const title = $(el).find('h2.gp-loop-title a').text().trim(); + const link = $(el).find('h2.gp-loop-title a').attr('href'); + const img = $(el).find('.gp-post-thumbnail img').attr('src'); + const ageText = $(el).find('.gp-loop-cats a').text().trim(); + const age = extractAgeFromText(ageText); + + if (title && link) { + results.push({ + title, + link, + img, + ageText, + age + }); + } + }); + + console.log(`FilmsPourEnfants found ${results.length} results`); + saveCache('search', query, results); + return results; + } catch (error) { + console.error('Error searching FilmsPourEnfants:', error.message); + return []; + } +} + +async function getMovieDetails(movieUrl) { + if (!movieUrl) return {}; + + // Check cache first + const cached = loadCache('detail', movieUrl); + if (cached) return cached; + + console.log('Fetching details for:', movieUrl); + + try { + const response = await axios.get(movieUrl, { + headers: { 'User-Agent': 'Mozilla/5.0' } + }); + const $ = cheerio.load(response.data); + const details = {}; + + // Title + details.title = $('h1.gp-entry-title').text().trim(); + + // Get metadata + $('.gp-entry-meta .gp-post-meta').each((_, el) => { + const text = $(el).text().trim(); + + if (text.includes('Année:')) { + details.year = $(el).find('a').text().trim(); + } else if (text.includes('Déconseillé aux moins de:')) { + details.ageText = $(el).find('a').text().trim(); + details.age = extractAgeFromText(details.ageText); + } else if (text.includes('Durée:')) { + details.duration = $(el).find('a').text().trim(); + } else if (text.includes('Thèmes:')) { + details.themes = []; + $(el).find('a').each((_, themeEl) => { + details.themes.push($(themeEl).text().trim()); + }); + } + }); + + // More detailed metadata + $('#gp-hub-details span').each((_, el) => { + const label = $(el).find('strong').text().trim(); + + if (label === 'Déconseillé aux moins de:') { + details.ageText = $(el).find('a').text().trim(); + details.age = extractAgeFromText(details.ageText); + } else if (label === 'Format:') { + details.format = $(el).find('a').text().trim(); + } else if (!details.year && label === 'Année:') { + details.year = $(el).find('a').text().trim(); + } else if (!details.duration && label === 'Durée:') { + details.duration = $(el).find('a').text().trim(); + } else if (label === 'Studio:') { + details.studio = []; + $(el).find('a').each((_, studioEl) => { + details.studio.push($(studioEl).text().trim()); + }); + } else if (label === 'Pays:') { + details.country = $(el).find('a').text().trim(); + } else if (label === 'Créateurs:') { + details.creators = []; + $(el).find('a').each((_, creatorEl) => { + details.creators.push($(creatorEl).text().trim()); + }); + } + }); + + // Get summary - first paragraph in the entry-text + details.summary = $('.gp-entry-text h4').first().text().trim(); + + // Get main image + details.img = $('.gp-post-thumbnail img').attr('src') || $('.gp-hub-header-thumbnail img').attr('src'); + + // Get messages section + let messages = ''; + $('.gp-entry-text h3').each((_, el) => { + const heading = $(el).text().trim(); + const paragraph = $(el).next('p').text().trim(); + if (heading && paragraph) { + messages += `${heading}: ${paragraph}\n\n`; + } + }); + details.messages = messages.trim(); + + // Get difficult scenes section + const difficultScenesHeading = $('.gp-entry-text h2:contains("SCÈNES DIFFICILES")'); + let difficultScenes = ''; + if (difficultScenesHeading.length) { + let current = difficultScenesHeading.next(); + while (current.length && current[0].tagName.toLowerCase() !== 'h2') { + if (current[0].tagName.toLowerCase() === 'h3' || current[0].tagName.toLowerCase() === 'p') { + difficultScenes += current.text().trim() + '\n\n'; + } + current = current.next(); + } + } + details.difficultScenes = difficultScenes.trim(); + + console.log(`Fetched details for: ${details.title}, Age: ${details.age}`); + saveCache('detail', movieUrl, details); + return details; + } catch (error) { + console.error('Error getting FilmsPourEnfants movie details:', error.message); + return {}; + } +} + +async function searchAndEnrich(query) { + try { + const results = await searchMovies(query); + return await Promise.all(results.map(async movie => { + const details = await getMovieDetails(movie.link); + + return { + title: movie.title, + year: details.year || null, + img: movie.img || details.img, + link: movie.link, + source: 'filmspourenfants', + // Format age for frontend display + age: details.age ? `${details.age}+` : movie.age ? `${movie.age}+` : "-", + ageDetails: { + France: details.age ? `${details.age}+` : movie.age ? `${movie.age}+` : "Non spécifié" + }, + duration: details.duration, + summary: details.summary, + themes: details.themes, + studio: details.studio, + creators: details.creators, + difficultScenes: details.difficultScenes, + messages: details.messages + }; + })); + } catch (error) { + console.error('FilmsPourEnfants searchAndEnrich error:', error.message); + return []; + } +} + +module.exports = { searchAndEnrich }; diff --git a/server.js b/server.js index 8b43cd4..ccf75ae 100644 --- a/server.js +++ b/server.js @@ -4,6 +4,7 @@ const cinecheck = require('./aggregators/cinecheck-adapter'); const commonsense = require('./aggregators/commonsense-adapter'); const filmages = require('./aggregators/filmages-adapter'); const filmstouspublics = require('./aggregators/filmstouspublics-adapter'); +const filmspourenfants = require('./aggregators/filmspourenfants-adapter'); const { mergeResults } = require('./merge'); const app = express(); @@ -19,7 +20,7 @@ app.get('/search', async (req, res) => { console.log('Query:', q); try { - const [cine, cs, fa, ftp] = await Promise.all([ + const [cine, cs, fa, ftp, fpe] = await Promise.all([ cinecheck.searchAndEnrich(q).catch(e => { console.error('Cinecheck failed:', e.message); return []; @@ -35,6 +36,10 @@ app.get('/search', async (req, res) => { filmstouspublics.searchAndEnrich(q).catch(e => { console.error('FilmsTousPublics failed:', e.message); return []; + }), + filmspourenfants.searchAndEnrich(q).catch(e => { + console.error('FilmsPourEnfants failed:', e.message); + return []; }) ]); @@ -42,8 +47,9 @@ app.get('/search', async (req, res) => { console.log('CSM results:', cs.length); console.log('Filmages results:', fa.length); console.log('FilmsTousPublics results:', ftp.length); + console.log('FilmsPourEnfants results:', fpe.length); - const merged = mergeResults([cine, cs, fa, ftp]); + const merged = mergeResults([cine, cs, fa, ftp, fpe]); res.json(merged); } catch (e) { console.error('General search error:', e);