| 1 |
#!/usr/bin/env python |
| 2 |
# -*- coding: utf-8 -*- |
| 3 |
# Recette Calibre — L'Équipe Premium |
| 4 |
# Auteur : Kabonix |
| 5 |
# Auth : eqn:EQN2014 (Basic ZXFuOkVRTjIwMTQ=) — extrait des DEX natifs de LEquipe v10.58.2 |
| 6 |
# API : https://dwh.lequipe.fr/api/v1/efr/news/{id} |
| 7 |
# Cover: scraping https://www.lequipe.fr/abonnement/kiosque/ → Twipe (id journal = 1627) |
| 8 |
|
| 9 |
from __future__ import absolute_import, division, print_function, unicode_literals |
| 10 |
|
| 11 |
import datetime |
| 12 |
import json |
| 13 |
import re |
| 14 |
import urllib.request |
| 15 |
|
| 16 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 17 |
|
| 18 |
|
| 19 |
class LEquipePremium(BasicNewsRecipe): |
| 20 |
title = "L'Équipe" |
| 21 |
__author__ = 'Kabonix' |
| 22 |
description = "Articles abonnés L'Équipe avec notes de matchs complètes" |
| 23 |
publisher = "L'Équipe" |
| 24 |
publication_type = 'newspaper' |
| 25 |
language = 'fr' |
| 26 |
encoding = 'utf-8' |
| 27 |
|
| 28 |
oldest_article = 1 |
| 29 |
no_stylesheets = True |
| 30 |
ignore_duplicate_articles = {'title', 'url'} |
| 31 |
remove_empty_feeds = True |
| 32 |
auto_cleanup = False |
| 33 |
delay = 1 |
| 34 |
|
| 35 |
# ------------------------------------------------------------------ # |
| 36 |
# Auth — hardcodé dans les DEX natifs de l'APK # |
| 37 |
# ------------------------------------------------------------------ # |
| 38 |
browser_user_agent = 'MOBILE-LEQUIPE/android/phone/10.58.2/premium/wifi/test' |
| 39 |
auth_header = 'Basic ZXFuOkVRTjIwMTQ=' # eqn:EQN2014 |
| 40 |
|
| 41 |
# ------------------------------------------------------------------ # |
| 42 |
# Couverture dynamique — scraping page kiosque Twipe # |
| 43 |
# ID fixe du titre "L'Équipe journal" chez Twipe : 1627 # |
| 44 |
# ------------------------------------------------------------------ # |
| 45 |
def get_cover_url(self): |
| 46 |
try: |
| 47 |
req = urllib.request.Request('https://www.lequipe.fr/abonnement/kiosque/', headers={'User-Agent': 'Mozilla/5.0'}) |
| 48 |
html = urllib.request.urlopen(req, timeout=10).read().decode('utf-8') |
| 49 |
m = re.search( |
| 50 |
r'https://eqp-eqp-webreader-production\.twipemobile\.com' |
| 51 |
r'/data/1627/covers/Preview-MEDIUM-\d+\.jpg[^"&]*', |
| 52 |
html, |
| 53 |
) |
| 54 |
if m: |
| 55 |
return m.group(0) |
| 56 |
except Exception: |
| 57 |
pass |
| 58 |
# Fallback : miniature journal par date |
| 59 |
today = datetime.datetime.now().strftime('%Y%m%d') |
| 60 |
return f'https://www.lequipe.fr/thumbnail/journal/{today}/1000/1490' |
| 61 |
|
| 62 |
# ------------------------------------------------------------------ # |
| 63 |
# Browser avec headers d'auth # |
| 64 |
# ------------------------------------------------------------------ # |
| 65 |
def get_browser(self, *args, **kwargs): |
| 66 |
br = BasicNewsRecipe.get_browser(self, *args, **kwargs) |
| 67 |
br.addheaders = [ |
| 68 |
('User-Agent', self.browser_user_agent), |
| 69 |
('Authorization', self.auth_header), |
| 70 |
('Accept', 'application/json'), |
| 71 |
] |
| 72 |
return br |
| 73 |
|
| 74 |
# ------------------------------------------------------------------ # |
| 75 |
# Filtre RSS → URL API # |
| 76 |
# Seuls les /Article/ sont premium ; /Actualites/ = brèves gratuites # |
| 77 |
# ------------------------------------------------------------------ # |
| 78 |
def get_article_url(self, article): |
| 79 |
url = BasicNewsRecipe.get_article_url(self, article) |
| 80 |
if not url: |
| 81 |
return None |
| 82 |
# Supprimer le fragment #at_medium=RSS_feeds |
| 83 |
url = url.split('#')[0] |
| 84 |
if '/Article/' not in url: |
| 85 |
return None |
| 86 |
m = re.search(r'/(\d+)$', url) |
| 87 |
if m: |
| 88 |
return f'https://dwh.lequipe.fr/api/v1/efr/news/{m.group(1)}' |
| 89 |
return None |
| 90 |
|
| 91 |
# ------------------------------------------------------------------ # |
| 92 |
# Bloc notes de match # |
| 93 |
# data_url → JSON Twipe avec titulaires, remplaçants, notes # |
| 94 |
# ------------------------------------------------------------------ # |
| 95 |
def parse_playing_field(self, data_url): |
| 96 |
try: |
| 97 |
req = urllib.request.Request(data_url, headers={'User-Agent': self.browser_user_agent}) |
| 98 |
raw = urllib.request.urlopen(req, timeout=10).read().decode('utf-8') |
| 99 |
d = json.loads(raw) |
| 100 |
except Exception: |
| 101 |
return '' |
| 102 |
|
| 103 |
html = '<hr style="margin:1em 0;"/>' |
| 104 |
equipes = d.get('equipes', []) |
| 105 |
|
| 106 |
# --- Score et note globale des équipes --- |
| 107 |
if len(equipes) == 2: |
| 108 |
e1, e2 = equipes[0], equipes[1] |
| 109 |
html += ( |
| 110 |
f'<table width="100%" style="margin-bottom:8px;border-collapse:collapse;">' |
| 111 |
f'<tr>' |
| 112 |
f'<td style="background:{e1["couleur"]};color:{e1["couleur_texte"]};' |
| 113 |
f'padding:6px;text-align:center;width:42%;font-weight:bold;">{e1["nom"]}</td>' |
| 114 |
f'<td style="text-align:center;padding:6px;width:16%;font-size:1.3em;font-weight:bold;">' |
| 115 |
f'{e1["score"]} – {e2["score"]}</td>' |
| 116 |
f'<td style="background:{e2["couleur"]};color:{e2["couleur_texte"]};' |
| 117 |
f'padding:6px;text-align:center;width:42%;font-weight:bold;">{e2["nom"]}</td>' |
| 118 |
f'</tr>' |
| 119 |
f'<tr>' |
| 120 |
f'<td style="text-align:center;color:{e1["couleur"]};font-weight:bold;">Note : {e1["note"]}</td>' |
| 121 |
f'<td></td>' |
| 122 |
f'<td style="text-align:center;color:{e2["couleur"]};font-weight:bold;">Note : {e2["note"]}</td>' |
| 123 |
f'</tr>' |
| 124 |
f'</table>' |
| 125 |
) |
| 126 |
|
| 127 |
# --- Titulaires et remplaçants par équipe --- |
| 128 |
banc = d.get('banc', []) |
| 129 |
for idx, equipe in enumerate(equipes): |
| 130 |
couleur = equipe['couleur'] |
| 131 |
couleur_texte = equipe['couleur_texte'] |
| 132 |
nom_equipe = equipe['nom'] |
| 133 |
|
| 134 |
titulaires = [j for j in d.get('titulaires', []) if j.get('couleur') == couleur] |
| 135 |
banc_equipe = banc[idx] if idx < len(banc) else {} |
| 136 |
remplacants = banc_equipe.get('remplacants', []) |
| 137 |
entraineur = banc_equipe.get('entraineur', {}) |
| 138 |
|
| 139 |
html += ( |
| 140 |
f'<h3 style="background:{couleur};color:{couleur_texte};' |
| 141 |
f'padding:4px 8px;margin-top:1em;">{nom_equipe}</h3>' |
| 142 |
f'<table width="100%" cellspacing="1" style="font-size:0.9em;">' |
| 143 |
f'<tr style="background:#ddd;">' |
| 144 |
f'<th style="text-align:left;padding:3px;">Joueur</th>' |
| 145 |
f'<th style="text-align:center;padding:3px;">Note</th>' |
| 146 |
f'<th style="padding:3px;"></th>' |
| 147 |
f'</tr>' |
| 148 |
) |
| 149 |
|
| 150 |
for j in titulaires: |
| 151 |
note = j.get('note', '-') |
| 152 |
nom = j.get('nom', '') |
| 153 |
buts = ' ⚽' * len(j.get('buts', [])) |
| 154 |
sortie = f"↓{j['min_sortie']}'" if j.get('min_sortie') else '' |
| 155 |
html += ( |
| 156 |
f'<tr>' |
| 157 |
f'<td style="padding:3px;">{nom}{buts}</td>' |
| 158 |
f'<td style="text-align:center;padding:3px;font-weight:bold;">{note}</td>' |
| 159 |
f'<td style="color:gray;font-size:0.85em;padding:3px;">{sortie}</td>' |
| 160 |
f'</tr>' |
| 161 |
) |
| 162 |
|
| 163 |
# Remplaçants notés uniquement |
| 164 |
for j in remplacants: |
| 165 |
note = j.get('note', '/') |
| 166 |
if note and note not in ('/', ''): |
| 167 |
nom = j.get('nom', '') |
| 168 |
entree = f"↑{j['min_entree']}'" if j.get('min_entree') else '' |
| 169 |
remplace = j.get('remplace', '') |
| 170 |
buts = ' ⚽' * len(j.get('buts', [])) |
| 171 |
html += ( |
| 172 |
f'<tr style="color:#555;">' |
| 173 |
f'<td style="padding:3px;font-style:italic;">' |
| 174 |
f'{nom}{buts} <span style="font-size:0.8em;">(rempl. {remplace})</span>' |
| 175 |
f'</td>' |
| 176 |
f'<td style="text-align:center;padding:3px;">{note}</td>' |
| 177 |
f'<td style="font-size:0.85em;padding:3px;">{entree}</td>' |
| 178 |
f'</tr>' |
| 179 |
) |
| 180 |
|
| 181 |
# Entraîneur |
| 182 |
if entraineur: |
| 183 |
html += ( |
| 184 |
f'<tr style="background:#f0f0f0;">' |
| 185 |
f'<td style="padding:3px;"><b>Entr. {entraineur.get("nom", "")}</b></td>' |
| 186 |
f'<td style="text-align:center;padding:3px;font-weight:bold;">' |
| 187 |
f'{entraineur.get("note", "-")}</td>' |
| 188 |
f'<td></td>' |
| 189 |
f'</tr>' |
| 190 |
) |
| 191 |
|
| 192 |
html += '</table>' |
| 193 |
|
| 194 |
# Arbitre |
| 195 |
arbitre = d.get('arbitre', {}) |
| 196 |
if arbitre: |
| 197 |
html += f'<p style="color:gray;font-size:0.85em;margin-top:4px;">Arbitre : {arbitre.get("nom", "")} — Note : {arbitre.get("note", "-")}</p>' |
| 198 |
|
| 199 |
html += '<hr style="margin:1em 0;"/>' |
| 200 |
return html |
| 201 |
|
| 202 |
# ------------------------------------------------------------------ # |
| 203 |
# Conversion JSON API → HTML lisible # |
| 204 |
# ------------------------------------------------------------------ # |
| 205 |
def strip_links(self, html): |
| 206 |
"""Supprime les balises <a> en gardant le texte""" |
| 207 |
return re.sub(r'<a[^>]*>(.*?)</a>', r'\1', html, flags=re.DOTALL) |
| 208 |
|
| 209 |
def preprocess_raw_html(self, raw_html, url): |
| 210 |
if '/api/v1/efr/news/' not in url: |
| 211 |
return raw_html |
| 212 |
|
| 213 |
try: |
| 214 |
data = json.loads(raw_html) |
| 215 |
except Exception: |
| 216 |
return '<html><body><p>Erreur JSON</p></body></html>' |
| 217 |
|
| 218 |
title = '' |
| 219 |
image_html = '' |
| 220 |
body = '' |
| 221 |
|
| 222 |
for item in data.get('items', []): |
| 223 |
obj = item.get('objet', {}) |
| 224 |
obj_type = obj.get('__type', '') |
| 225 |
|
| 226 |
# --- En-tête article (titre + image) --- |
| 227 |
if obj_type == 'article_feature': |
| 228 |
title = obj.get('long_title', obj.get('title', '')) |
| 229 |
|
| 230 |
media = obj.get('media', {}) |
| 231 |
img_url = media.get('url', '') |
| 232 |
if img_url: |
| 233 |
img_url = img_url.replace('{width}', '800').replace('{height}', '600').replace('{quality}', '85') |
| 234 |
legende = media.get('legende', '') |
| 235 |
image_html = ( |
| 236 |
f'<figure style="margin:0 0 1em 0;">' |
| 237 |
f'<img src="{img_url}" style="max-width:100%;"/>' |
| 238 |
f'<figcaption style="font-size:0.8em;color:#666;">{legende}</figcaption>' |
| 239 |
f'</figure>' |
| 240 |
) |
| 241 |
|
| 242 |
# --- Corps de l'article --- |
| 243 |
elif obj_type == 'article_body': |
| 244 |
for p in obj.get('paragraphs', []): |
| 245 |
layout = p.get('layout', '') |
| 246 |
content = p.get('content', '') |
| 247 |
ptitle = p.get('title', '') |
| 248 |
|
| 249 |
if layout == 'chapo': |
| 250 |
body += f'<p style="font-size:1.1em;font-style:italic;">{self.strip_links(content)}</p>' |
| 251 |
|
| 252 |
elif layout == 'text': |
| 253 |
if ptitle: |
| 254 |
body += f'<h2>{ptitle}</h2>' |
| 255 |
body += f'<p>{self.strip_links(content)}</p>' |
| 256 |
|
| 257 |
elif layout == 'note': |
| 258 |
note_obj = p.get('note') |
| 259 |
if note_obj and note_obj.get('layout') == 'team': |
| 260 |
# Titre de section équipe (ex : "Chelsea — Note : 3,8") |
| 261 |
label = note_obj.get('label', '') |
| 262 |
rating = note_obj.get('rating_label', note_obj.get('rating', '')) |
| 263 |
color = note_obj.get('background_color', '#333') |
| 264 |
tcolor = note_obj.get('text_color', '#fff') |
| 265 |
body += f'<h2 style="background:{color};color:{tcolor};padding:4px 8px;margin-top:1.2em;">{label} — Note : {rating}</h2>' |
| 266 |
elif content: |
| 267 |
# Note individuelle joueur avec photo optionnelle |
| 268 |
img_obj = p.get('image', {}) |
| 269 |
img_url = img_obj.get('url', '') if img_obj else '' |
| 270 |
if img_url: |
| 271 |
img_url = img_url.replace('{width}', '120').replace('{height}', '120').replace('{quality}', '80') |
| 272 |
body += ( |
| 273 |
f'<table style="margin:0.5em 0;width:100%;">' |
| 274 |
f'<tr>' |
| 275 |
f'<td style="width:120px;vertical-align:top;">' |
| 276 |
f'<img src="{img_url}" style="width:110px;"/>' |
| 277 |
f'</td>' |
| 278 |
f'<td style="vertical-align:top;padding-left:8px;">' |
| 279 |
f'{self.strip_links(content)}</td>' |
| 280 |
f'</tr></table>' |
| 281 |
) |
| 282 |
else: |
| 283 |
body += f'<p>{self.strip_links(content)}</p>' |
| 284 |
|
| 285 |
elif layout == 'playing_field': |
| 286 |
data_url = p.get('data', '') |
| 287 |
if data_url: |
| 288 |
body += self.parse_playing_field(data_url) |
| 289 |
|
| 290 |
elif layout == 'link': |
| 291 |
pass # on ignore les "lire aussi" |
| 292 |
|
| 293 |
# on ignore aussi layout_DFP / pub_DFP / pub |
| 294 |
|
| 295 |
return f'<html><head><meta charset="utf-8"><title>{title}</title></head><body>{image_html}<h1>{title}</h1>{body}</body></html>' |
| 296 |
|
| 297 |
# ------------------------------------------------------------------ # |
| 298 |
# Flux RSS # |
| 299 |
# ------------------------------------------------------------------ # |
| 300 |
feeds = [ |
| 301 |
('À la une', 'https://dwh.lequipe.fr/api/edito/rss?path=/'), |
| 302 |
('Football', 'https://dwh.lequipe.fr/api/edito/rss?path=/Football'), |
| 303 |
('Tennis', 'https://dwh.lequipe.fr/api/edito/rss?path=/Tennis'), |
| 304 |
('Cyclisme', 'https://dwh.lequipe.fr/api/edito/rss?path=/Cyclisme-sur-route'), |
| 305 |
('Rugby', 'https://dwh.lequipe.fr/api/edito/rss?path=/Rugby'), |
| 306 |
('Basket', 'https://dwh.lequipe.fr/api/edito/rss?path=/Basket'), |
| 307 |
('Formule 1', 'https://dwh.lequipe.fr/api/edito/rss?path=/Formule-1'), |
| 308 |
('Athlétisme', 'https://dwh.lequipe.fr/api/edito/rss?path=/Athletisme'), |
| 309 |
('Handball', 'https://dwh.lequipe.fr/api/edito/rss?path=/Handball'), |
| 310 |
] |