WP URL Suspension Sync A lightweight Python script that compares all URLs from a WordPress sitemap against those exported in a Google Search Console CSV, and automatically sets to pending any posts/pages whose URLs are missing from the CSV—ideal for batch-testing with a configurable limit before full rollout.

potatura.py

from urllib.parse import urlparse
import csv
import re
import requests
import xml.etree.ElementTree as ET
import random

def estrai_url_sitemap(url):
    urls = []

    def process_sitemap(sitemap_url):
        try:
            response = requests.get(sitemap_url)
            response.raise_for_status()
            root = ET.fromstring(response.content)
            # Determina se è un index o una sitemap normale
            if root.tag.endswith('sitemapindex'):
                for sitemap in root.findall('.//{*}sitemap'):
                    loc = sitemap.find('{*}loc')
                    if loc is not None and loc.text:
                        process_sitemap(loc.text)
            elif root.tag.endswith('urlset'):
                for url_tag in root.findall('.//{*}url'):
                    loc = url_tag.find('{*}loc')
                    if loc is not None and loc.text:
                        urls.append(loc.text)
        except Exception as e:
            print(f"Errore durante il processamento di {sitemap_url}: {e}")

    process_sitemap(url)
    return urls

# # Esempio d'uso:
# if __name__ == "__main__":
#     sitemap_urls = estrai_url_sitemap("https://www.trovalost.it/sitemap_index.xml")
#     for u in sitemap_urls:
#         print(u)


def estrai_url_da_csv(file_path):
    """
    Estrae tutte le URL presenti in tutte le celle di un file CSV.

    :param file_path: percorso al file .csv
    :return: lista di URL trovate
    """
    urls = []
    url_pattern = re.compile(r'https?://\S+')
    with open(file_path, newline='', encoding='utf-8') as f:
        reader = csv.reader(f)
        for row in reader:
            for cell in row:
                # trova tutte le sottostringhe che corrispondono a http:// o https://
                for match in url_pattern.findall(cell):
                    urls.append(match)
    return urls

# Esempio d’uso:
# if __name__ == "__main__":
#     file_csv = 'porta_traffico-trovalost.csv'
#     lista_urls = estrai_url_da_csv(file_csv)
#     # stampa in formato “array testo”
#     print(lista_urls)

# —————————————————————————————————————————————————————————
# FUNZIONI DI ESTRAZIONE (riutilizzano il tuo codice)
# —————————————————————————————————————————————————————————

def estrai_url_sitemap(sitemap_url):
    urls = []
    def _process(surl):
        r = requests.get(surl)
        r.raise_for_status()
        root = ET.fromstring(r.content)
        if root.tag.endswith('sitemapindex'):
            for sm in root.findall('.//{*}sitemap'):
                loc = sm.find('{*}loc')
                if loc is not None and loc.text:
                    _process(loc.text)
        elif root.tag.endswith('urlset'):
            for u in root.findall('.//{*}url'):
                loc = u.find('{*}loc')
                if loc is not None and loc.text:
                    urls.append(loc.text)
    _process(sitemap_url)
    return urls

def estrai_url_da_csv(file_path):
    urls = []
    pattern = re.compile(r'https?://\S+')
    with open(file_path, newline='', encoding='utf-8') as f:
        for row in csv.reader(f):
            for cell in row:
                urls += pattern.findall(cell or '')
    return urls

# —————————————————————————————————————————————————————————
# FUNZIONI D’INTERAZIONE CON WP-REST
# —————————————————————————————————————————————————————————

def get_post_id_by_url(wp_api_base, auth, url, post_type='posts'):
    """
    Tenta di recuperare l'ID di un post/page dato il suo URL completo.
    Si basa sullo slug (ultima parte dell'URL).
    """
    slug = urlparse(url).path.strip('/').split('/')[-1]
    endpoint = f"{wp_api_base}/wp/v2/{post_type}"
    resp = requests.get(endpoint, params={'slug': slug}, auth=auth)
    resp.raise_for_status()
    data = resp.json()
    if data:
        return data[0]['id']
    return None

def set_status(wp_api_base, auth, post_id, status='pending', post_type='posts'):
    """
    Imposta lo status di un post/page via REST.
    """
    endpoint = f"{wp_api_base}/wp/v2/{post_type}/{post_id}"
    payload = {'status': status}
    resp = requests.post(endpoint, json=payload, auth=auth)
    resp.raise_for_status()
    return resp.json()

# —————————————————————————————————————————————————————————
# FUNZIONE PRINCIPALE
# —————————————————————————————————————————————————————————

def sync_suspend_urls(
    sitemap_url: str,
    csv_path: str,
    wp_api_base: str,
    auth: tuple,
    post_type: str = 'posts',
    status: str = 'pending',
    limit: int = None
):
    """
    1. Legge tutti gli URL dalla sitemap.
    2. Legge tutti gli URL dal CSV.
    3. Trova quelli da sospendere = sitemap - csv.
    4. Limita a `limit` elementi (se non None).
    5. Per ciascuno, trova l'ID WP e ne cambia lo status.
    6. Ritorna un report di tuple (url, result).
    """
    sitemap_urls = estrai_url_sitemap(sitemap_url)
    csv_urls     = estrai_url_da_csv(csv_path)
    
    to_suspend = list(set(sitemap_urls) - set(csv_urls))
    if limit:
        to_suspend = to_suspend[:limit]
    
    # print ( to_suspend )

    report = []
    for url in to_suspend:
        try:
            pid = get_post_id_by_url(wp_api_base, auth, url, post_type)
            if not pid:
                report.append((url, 'SKIPPED: post non trovato'))
                continue
            res = set_status(wp_api_base, auth, pid, status, post_type)
            report.append((url, f"OK: status impostato su '{status}' (ID {pid})"))
            print(url, ' OK ')
        except Exception as e:
            report.append((url, f"ERROR: {e}"))
            print(url, ' KO ')
    
    return report

# —————————————————————————————————————————————————————————
# ESEMPIO D’USO
# —————————————————————————————————————————————————————————

if __name__ == "__main__":
    # Configura qui i parametri:
    SITEMAP_URL = "https://www.sito.it/sitemap_index.xml"
    CSV_PATH    = "porta_traffico-sito.csv"
    WP_API_BASE = "https://www.sito.it/wp-json"
    # auth = (username, application_password)
    AUTH        = ("ciuppaflesx", "9imU xu04 chfU Sx1h EP0c lufc")
    
    fernando = random.randint(5,500) 
    print ( fernando )

    # Primo test solo su limit URL:
    report = sync_suspend_urls(
        sitemap_url=SITEMAP_URL,
        csv_path=CSV_PATH,
        wp_api_base=WP_API_BASE,
        auth=AUTH,
        post_type='posts',    # o 'pages'
        status='pending',     # o 'draft'
        limit = fernando
    )
    
    # Stampiamo il report
    for url, msg in report:
        print(f"{msg:40} → {url}")