欧美性猛交XXXX免费看蜜桃,成人网18免费韩国,亚洲国产成人精品区综合,欧美日韩一区二区三区高清不卡,亚洲综合一区二区精品久久

from flask import Flask, render_template, request, session, jsonifyimport sqlite3import jiebaimport mathimport stringimport re
app = Flask(__name__)DATABASE = 'data.db'

def create_database():    conn = sqlite3.connect(DATABASE)    c = conn.cursor()    c.execute('''CREATE VIRTUAL TABLE IF NOT EXISTS contents USING fts5(        title, url , favicon , description , content , keywords , date,img )''')    conn.commit()    conn.close()

def tokenize(title):    words = [word for word in jieba.cut(title) if word not in string.punctuation]  # 分詞并去掉標點(diǎn)符號    keywords = [word for word in words if len(word) > 1]  # 去掉單個(gè)字    keywords = list(set(keywords))  # 去重    keywords.sort(key=words.index)  # 按在title中出現的順序排序    keyword_str = ' '.join(keywords)  # 將關(guān)鍵詞列表轉換為以空格分隔的字符串    keyword_str = ''.join(filter(lambda x: x not in string.punctuation, keyword_str))  # 去掉字符串中的標點(diǎn)符號    return keyword_str

def search_contents(query, offset, per_page):    conn = sqlite3.connect(DATABASE)    conn.row_factory = sqlite3.Row    c = conn.cursor()    c.execute('SELECT COUNT(*) FROM contents WHERE keywords MATCH :query',              {'query': query})    total_results = c.fetchone()[0]  # 獲取搜索結果總數    total_pages = calculate_total_pages(total_results, per_page)  # 計算總頁(yè)數    if offset >= total_results:        offset = (total_pages - 1) * per_page    c.execute('SELECT title, url, favicon, description, keywords, date FROM contents WHERE keywords MATCH :query LIMIT :per_page OFFSET :offset',              {'query': query, 'per_page': per_page, 'offset': offset})    rows = c.fetchall()    conn.close()    return {'results': [dict(row) for row in rows],            'total_results': total_results,            'total_pages': total_pages}

def calculate_total_pages(total_results, per_page):    return math.ceil(total_results / per_page)

@app.before_requestdef session_online():    session_id = request.cookies.get('session_id')    online = session.get('Online', 0)    if session_id is not None:        online += 1    session['Online'] = online

@app.route('/get_suggestions')def get_suggestions():    query = request.args.get('q')
    conn = sqlite3.connect(DATABASE)    c = conn.cursor()
    # 在contents表中查詢(xún)包含輸入關(guān)鍵詞的title列，最多返回5個(gè)結果    c.execute('SELECT title FROM contents WHERE title LIKE ? LIMIT 5', ('%' + query + '%',))    suggestions = [row[0] for row in c.fetchall()]
    conn.close()
    return jsonify(suggestions=suggestions)

@app.route('/', methods=['GET'])def index():    # 處理搜索請求    query = request.args.get('q', '')  # 獲取查詢(xún)關(guān)鍵詞，默認為空字符串    page = request.args.get('page', '1')  # 獲取當前頁(yè)數，默認為第1頁(yè)    per_page = 10  # 每頁(yè)顯示的結果數量    offset = (int(page) - 1) * per_page  # 計算偏移量    online = session.get('Online', 0)    if query:        # 搜索網(wǎng)頁(yè)內容        content_result = search_contents(tokenize(query), offset, per_page)
        return render_template('index.html',                               query=query,                               content_result=content_result['results'],                               total_results=content_result['total_results'],  # 顯示搜索結果總數                               total_pages=content_result['total_pages'],                               current_page=int(page),                               online=online)    else:        return render_template('index.html',                               online=online)

if __name__ == '__main__':    create_database()    app.secret_key = 'pyxueba'    app.run(debug=True)

import requestsfrom bs4 import BeautifulSoupimport sqlite3import jiebaimport threadingimport timeimport randomimport stringimport refrom datetime import dateimport base64class Crawler:    def get_image_data_uri(self,image_url):     # 發(fā)起GET請求獲取圖像數據     response = requests.get(image_url)     image_data = response.content
     # 將圖像數據轉換為base64格式     base64_data = base64.b64encode(image_data).decode('utf-8')
     # 構建包含base64圖像數據的data URI     data_uri = f'data:image/x-icon;base64,{base64_data}'
     # 返回data URI     return data_uri    def __init__(self, max_depth=3, num_workers=10):        self.max_depth = max_depth        self.num_workers = num_workers        self.conn = sqlite3.connect('data.db', check_same_thread=False)        self.lock = threading.Lock()        self.url_queue = []        self.crawled_urls = set()
        self.create_tables()        self.add_urls(['https://www.hao123.com/'])        self.run()
    def create_tables(self):        c = self.conn.cursor()        c.execute('''CREATE VIRTUAL TABLE IF NOT EXISTS contents USING fts5 (                    title ,                    url ,                    favicon ,                    description ,                    keywords ,                    date ,                    img )''')        self.conn.commit()
    def add_urls(self, urls):        with self.lock:            self.url_queue.extend(urls)
    def crawl_and_save(self, url, depth=0):        try:            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'            }            if '.ico' not in url and '.jpg' not in url and '.png' not in url and 'javascript:;' not in url and '#' not in url and 'javascript:void(0)' not in url and 'javascript' not in url and url != '':             response = requests.get(url, headers=headers, timeout=2.5)             response.raise_for_status()            else:             print(f'無(wú)效：{url} ')             return        except (requests.exceptions.RequestException, requests.exceptions.HTTPError) as e:            print(f'無(wú)法獲取鏈接 {url}：{e}')            return
        content_type = response.headers.get('content-type')        if not content_type or not content_type.startswith('text/html'):            return
        raw_html = response.content        html_text = response.text        soup = BeautifulSoup(raw_html, 'html.parser')        title_tag = soup.title        title=''        if title_tag is None:            print(f'鏈接 {url} 未找到標題，跳過(guò)...')            return        if title_tag is not None:          title = title_tag.string.strip()        if not title:            print(f'鏈接 {url} 標題為空，跳過(guò)...')            return        title2 = ' '.join(jieba.cut(title))        title2 = ''.join([char for char in title if char not in string.punctuation])  # 去掉標點(diǎn)符號
        with self.lock:            if url in self.crawled_urls:                return
            date_regex = re.compile(r'\d{4}-\d{2}-\d{2}')  # 假設日期格式為YYYY-MM-DD            date_match = date_regex.search(html_text)            if date_match:               shijian = date_match.group()            else:             # 使用meta標簽提取日期信息               date_tag = soup.select_one('meta[name='date'], meta[name='pubdate']')               shijian = date_tag.get('content') if date_tag else None
               # 如果日期為空，使用當前日期            if not shijian or shijian.strip() == '':               shijian = str(date.today())            print(shijian)            try:                keywords = self.extract_keywords(title2)                description, favicon, img_urls = self.extract_page_info(soup)                if favicon:                 favicon=self.get_image_data_uri(favicon);                c = self.conn.cursor()                c.execute(                    'INSERT INTO contents(title, url, favicon, description, keywords, date, img) VALUES (?, ?, ?, ?, ?, ?, ?)',                    (title, url, favicon, description, ','.join(keywords), shijian, '\n'.join(img_urls)))                self.conn.commit()                self.crawled_urls.add(url)                print(f'正在爬取 '{url}' 并保存到數據庫...')            except sqlite3.IntegrityError:                pass
        if depth < self.max_depth:            links = soup.find_all('a', href=True)            for link in links:                next_url = link['href']                if not next_url.startswith('http'):                    next_url = url + next_url                self.add_urls([next_url])  # 添加新的URL到隊列中
    @staticmethod    def extract_keywords(title):     words = [word for word in jieba.cut(title) if word not in string.punctuation]  # 分詞并去掉標點(diǎn)符號     keywords = [word for word in words if len(word) > 0]  # 去掉單個(gè)字     keywords = list(set(keywords))  # 去重     keywords.sort(key=words.index)  # 按在 title 中出現的順序排序     #keywords = keywords[:10]  # 只保留前 10 個(gè)關(guān)鍵詞     return keywords
    @staticmethod    def extract_page_info(soup):        description = ''        favicon = ''        img_urls = []
        meta_description = soup.find('meta', attrs={'name': 'description'})        if meta_description and meta_description.has_attr('content'):            description = meta_description['content']
        link_favicon = soup.find('link', attrs={'rel': 'icon'})        if link_favicon and link_favicon.has_attr('href'):            favicon = link_favicon['href']
        img_links = soup.find_all('img')        img_urls = [img.get('src') for img in img_links]        img_urls = [img for img in img_urls if img is not None]
        return description, favicon, img_urls
    def worker(self):        while True:            url = None            with self.lock:                if self.url_queue:                    url = self.url_queue.pop(0)
            if url is None:                break
            # 添加隨機延時(shí)            delay = random.uniform(1, 3)            time.sleep(delay)
            self.crawl_and_save(url)
    def run(self):        threads = []        for _ in range(self.num_workers):            t = threading.Thread(target=self.worker)            t.start()            threads.append(t)
        for t in threads:            t.join()
        self.conn.close()            #self.run()

if __name__ == '__main__':    crawler = Crawler(max_depth=5, num_workers=5)