سلام،

علت این مشکل کاراکترهای غیر مجاز در نام فایل هاست.

از متد زیر استفاده کنید تا مشکل حل شود:

def store(self, data, filename):
    # ایجاد دایرکتوری در صورت عدم وجود
    directory = "fixtures/adv"
    if not os.path.exists(directory):
        os.makedirs(directory)
    # جایگزینی کاراکترهای غیرمجاز در نام فایل
    filename = "".join(c if c.isalnum() or c in (' ', '.', '_') else '_' for c in filename)
    filepath = os.path.join(directory, f"{filename}.json")
    with open(filepath, "w") as f:
        f.write(json.dumps(data, ensure_ascii=False, indent=4))
    print(filepath)

تغییراتی در کدها اعمال شد برای لینک‌های غیر مجاز که skip بشن و وقتی ctrl + c میزنیم مدیریت شود و چند مورد کوچک دیگر که در ادامه میارم:

فایل crawler.py:

import os
import json
from abc import ABC, abstractmethod
import requests
from bs4 import BeautifulSoup
BACE_LINKS = "https://{}.craigslist.org/search/hhh?availabilityMode=0&lang=fr&cc=fr#search=1~gallery~0~2"
class CrawlerBace(ABC):
    @abstractmethod
    def start(self, store=False):
        pass
    @abstractmethod
    def store(self, data, filename=None):
        pass
    @staticmethod
    def get(link):
        try:
            response = requests.get(link)
        except requests.HTTPError:
            return None
        return response
class LinkCrawler(CrawlerBace):
    def __init__(self, cites):
        self.cites = cites
    def find_links(self, html_doc):
        soup = BeautifulSoup(html_doc, features='html.parser')
        return soup.find_all('a')
    def start_crawl(self, url):
        response = self.get(url)
        new_links = self.find_links(response.text)
        return new_links
    def start(self, store=False):
        adv_link = list()
        for city in self.cites:
            links = self.start_crawl(BACE_LINKS.format(city))
            print(f"city: {city}, total: {len(links)}")
            adv_link.extend(links)
        if store:
            valid_links = [li.get("href") for li in adv_link if li.get("href") and li.get("href").startswith("http")]
            self.store(valid_links)
        return adv_link
    def store(self, data, filename=None):
        if not filename:
            filename = "fixtures/data.json"
        with open(filename, "w") as f:
            f.write(json.dumps(data))
class DataCrawle(CrawlerBace):
    def __init__(self):
        self.links = self.__load_link()
        self.parserr = AdvertisementParser()
    @staticmethod
    def __load_link():
        with open("fixtures/data.json", 'r') as f:
            links = json.loads(f.read())
            return links
    def start(self, store=False):
        try:
            for link in self.links:
                if not link.startswith("http"):
                    print(f"Skipping invalid URL: {link}")
                    continue
                response = requests.get(link)
                data = self.parserr.parser(response.text)
                print(data)  # چاپ داده‌ها برای دیباگ
                if store:
                    self.store(data, data.get("post_id", "sample"))
        except KeyboardInterrupt:
            print("Process interrupted by user. Exiting gracefully...")
            return
    def store(self, data, filename):
        # ایجاد دایرکتوری در صورت عدم وجود
        directory = "fixtures/adv"
        if not os.path.exists(directory):
            os.makedirs(directory)
        # جایگزینی کاراکترهای غیرمجاز در نام فایل
        filename = "".join(c if c.isalnum() or c in (' ', '.', '_') else '_' for c in filename)
        filepath = os.path.join(directory, f"{filename}.json")
        with open(filepath, "w") as f:
            f.write(json.dumps(data, ensure_ascii=False, indent=4))
        print(filepath)
class AdvertisementParser:
    def __init__(self):
        self.soup = None
    @property
    def titel(self):
        titel_tag = self.soup.find('span', attrs={"id": "titletextonly"})
        if titel_tag:
            return titel_tag.text
    @property
    def price(self):
        price_tag = self.soup.find("span", attrs={"class": "price"})
        if price_tag:
            return price_tag.text
    @property
    def body(self):
        body_tag = self.soup.select_one("#postingbody")
        if body_tag:
            return body_tag.text
    @property
    def post_id(self):
        selector = "body > section > section > section > div.postinginfos > p:nth-child(1)"
        id_tag = self.soup.select_one(selector)
        if id_tag:
            return id_tag.text.replace('post id', '').strip()
    @property
    def creat_time(self):
        selector = "body > section > section > section > div.postinginfos > p.postinginfo.reveal > time"
        time = self.soup.select_one(selector)
        if time:
            return time.attrs["datetime"]
    def parser(self, html_data):
        self.soup = BeautifulSoup(html_data, "html.parser")
        data = dict(
            titel=self.titel, price=self.price, post_id=self.post_id,
            creat_time=self.creat_time, modified_time=None
        )
        return data

فایل com.py:

from crawler import LinkCrawler, DataCrawle

فایل main.py:

import sys
from com import LinkCrawler, DataCrawle
if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("Usage: python main.py [find_link | extract_pages]")
        sys.exit(1)
    switch = sys.argv[1]
    if switch == "find_link":
        crawler = LinkCrawler(cites=['berlin', 'paris'])
        crawler.start(store=True)
    elif switch == "extract_pages":
        cr = DataCrawle()
        cr.start(store=True)
    else:
        print("Invalid option. Use 'find_link' or 'extract_pages'.")
        sys.exit(1)