最新文章

with sync_playwright() as p:
    # 启动浏览器（Chromium示例）
    browser = p.chromium.launch(headless=True)  # 调试时可关闭无头模式
context = browser.new_context()
page = context.new_page()

try:
    # 设置大尺寸视口模拟最大化
    page.set_viewport_size({"width": SCREENSHOT_WIDTH, "height": SCREENSHOT_HEIGHT})

    # 访问目标页面
    page.goto(URL, timeout=60000)
    print("页面加载完成")
    date_str = get_current_date_str()

    # 处理Cookie弹窗
    try:
        page.click(COOKIE_BUTTON_SELECTOR, timeout=5000)
        print("已点击接受Cookie按钮")
    except Exception as e:
        print(f"未找到Cookie按钮或处理失败: {e}")

    # 等待目标元素加载
    element = page.wait_for_selector(TARGET_ELEMENT_SELECTOR, timeout=15000)

    # 滚动到元素确保可见
    element.scroll_into_view_if_needed()

    # 生成唯一文件名
    timestamp = int(time.time())
    filename = f"calendar_section_{date_str}.png"

    # 对指定元素截图
    element.screenshot(path=f"calendar\{filename}")
    print(f"截图已保存至: {filename}")

finally:
    # 确保关闭浏览器
    context.close()
    browser.close()

print("操作完成")

URL = "https://weather.cma.cn/web/weather/58946.html"
TARGET_ELEMENT_SELECTOR_1 = "body > div.container > div:nth-child(2) > div > div"  # 目标元素选择器
TARGET_ELEMENT_SELECTOR_2 = "body > div.container >     div.row.mt15 > div.col-xs-9 > div:nth-child(1)"  # 目标元素选择器
SCREENSHOT_WIDTH = 1920  # 截图宽度
SCREENSHOT_HEIGHT = 1080  # 截图高度

with sync_playwright() as p:
# 启动浏览器（Chromium示例）
browser = p.chromium.launch(headless=True)  # 调试时可关闭无头模式
context = browser.new_context()
page = context.new_page()    
try:
    # 设置大尺寸视口模拟最大化
    page.set_viewport_size({"width": SCREENSHOT_WIDTH, "height": SCREENSHOT_HEIGHT})

    # 访问目标页面
    page.goto(URL, timeout=60000)
    print("页面加载完成")
    date_str = get_current_date_str()


    # 等待目标元素加载
    element = page.wait_for_selector(TARGET_ELEMENT_SELECTOR_1, timeout=15000)

    # 滚动到元素确保可见
    element.scroll_into_view_if_needed()

    # 生成唯一文件名
    timestamp = int(time.time())
    image_name_1 = time.strftime('%Y-%m-%d') + '-1'
    filename_1 = r"D:\docs\tianqi\%s.png" % image_name_1

    element.screenshot(path=filename_1)

    # 等待目标元素加载
    element = page.wait_for_selector(TARGET_ELEMENT_SELECTOR_2, timeout=15000)

    # 滚动到元素确保可见
    element.scroll_into_view_if_needed()

    # 生成唯一文件名
    timestamp = int(time.time())
    image_name_2 = time.strftime('%Y-%m-%d') + '-2'
    filename_2 = r"D:\docs\tianqi\%s.png" % image_name_2
    print(filename_1)
    print(filename_2)

    # 对指定元素截图
    #pa = "D:\docs\calendar\" + filename

    element.screenshot(path=filename_2)
    print(f"截图已保存至: {filename_1}")

    img = Image.open("d:/docs/tianqi/%s.png" % image_name_1)
    newimg = img.resize((870,245))
    newimg.save(("d:/docs/tianqi/%s.png" % image_name_1))
    img1 = Image.open("d:/docs/tianqi/%s.png" % image_name_1)
    size1 = img1.size
    img2 = Image.open("d:/docs/tianqi/%s.png" % image_name_2)
    size2 = img2.size
    joint = Image.new("RGB", (size1[0], size1[1]+size2[1]))
    loc1, loc2 = (0, 0), (0, size1[1])
    joint.paste(img1, loc1)
    joint.paste(img2, loc2)
    image_name = time.strftime('%Y-%m-%d')
    joint.save("d:/docs/tianqi/pt-%s.png" % image_name)

finally:
    # 确保关闭浏览器
    context.close()
    browser.close()

pip install flask playwright beautifulsoup4 reportlab
playwright install

app.py

import asyncio
import re
import io
import zipfile

from flask import Flask, render_template_string, request, send_file
from playwright.async_api import async_playwright
from bs4 import BeautifulSoup

from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
from reportlab.lib.styles import getSampleStyleSheet
from reportlab.lib.pagesizes import letter
from reportlab.lib.units import inch

app = Flask(__name__)

# =========================
# 抓取文章
# =========================
async def fetch_article(url):
    async with async_playwright() as p:
        browser = await p.chromium.launch(headless=True)
        page = await browser.new_page()

        await page.goto(url, timeout=60000)
        await page.wait_for_selector("article")

        html = await page.content()
        await browser.close()

    soup = BeautifulSoup(html, "html.parser")

    title_tag = soup.find("h1")
    title = title_tag.get_text(strip=True) if title_tag else "No Title Found"

    article = soup.find("article")
    paragraphs = []

    if article:
        for p in article.find_all("p"):
            text = p.get_text(strip=True)
            if not text:
                continue

            # 去广告关键词
            if any(keyword in text.lower() for keyword in [
                "advertisement",
                "sponsored",
                "read more",
                "subscribe",
                "sign up",
                "related",
                "continue reading"
            ]):
                continue

            paragraphs.append(text)

    content = "\n\n".join(paragraphs)
    content = clean_text(content)

    return title, content


def clean_text(text):
    text = re.sub(r'\n\s*\n', '\n\n', text)
    return text.strip()


# =========================
# 生成 PDF
# =========================
def generate_pdf(title, content):
    buffer = io.BytesIO()
    doc = SimpleDocTemplate(buffer, pagesize=letter)
    elements = []

    styles = getSampleStyleSheet()
    title_style = styles["Heading1"]
    body_style = styles["BodyText"]

    elements.append(Paragraph(title, title_style))
    elements.append(Spacer(1, 0.5 * inch))

    for paragraph in content.split("\n\n"):
        elements.append(Paragraph(paragraph, body_style))
        elements.append(Spacer(1, 0.2 * inch))

    doc.build(elements)
    buffer.seek(0)
    return buffer


# =========================
# HTML 页面
# =========================
HTML_TEMPLATE = """
<!DOCTYPE html>
<html>
<head>
    <title>MSN 批量下载器</title>
</head>
<body style="font-family: Arial; text-align: center; margin-top: 50px;">
    <h1>MSN 文章批量下载 PDF</h1>
    <p>每行一个链接</p>
    <form method="post">
        <textarea name="urls" rows="10"
                  style="width: 700px; padding: 10px;"
                  placeholder="每行粘贴一个文章链接"
                  required></textarea>
        <br><br>
        <button type="submit" style="padding: 10px 20px;">
            批量下载
        </button>
    </form>
</body>
</html>
"""


@app.route("/", methods=["GET", "POST"])
def index():
    if request.method == "POST":
        urls_text = request.form.get("urls")
        urls = [u.strip() for u in urls_text.split("\n") if u.strip()]

        zip_buffer = io.BytesIO()

        with zipfile.ZipFile(zip_buffer, "w", zipfile.ZIP_DEFLATED) as zipf:
            for url in urls:
                try:
                    title, content = asyncio.run(fetch_article(url))

                    if not content:
                        continue

                    pdf_buffer = generate_pdf(title, content)

                    # 自动清理文件名
                    safe_title = re.sub(r'[\\/*?:"<>|]', "", title)
                    safe_title = safe_title.strip()[:80]

                    filename = safe_title + ".pdf"

                    zipf.writestr(filename, pdf_buffer.read())

                except Exception as e:
                    print("抓取失败:", url, e)

        zip_buffer.seek(0)

        return send_file(
            zip_buffer,
            as_attachment=True,
            download_name="msn_articles.zip",
            mimetype="application/zip"
        )

    return render_template_string(HTML_TEMPLATE)


if __name__ == "__main__":
    app.run(debug=True)

python app.py

http://127.0.0.1:5000

粘贴多个URL
        ↓
逐个 Playwright 渲染
        ↓
提取标题 + 正文
        ↓
生成独立 PDF
        ↓
打包 ZIP
        ↓
浏览器下载

#include <iostream>
#include <string>
using namespace std;

int main() {
    string s1 = "hello";
    string s2 = "world";

    // 拼接
    string s3 = s1 + " " + s2;   // "hello world"

    // 长度
    cout << s3.length() << endl;  // 11

    // 访问字符
    cout << s3[0] << endl;        // 'h'

    // 查找子串
    int pos = s3.find("world");    // 返回6
    if (pos != string::npos) {
        cout << "找到了，位置：" << pos << endl;
    }

    // 截取子串
    string sub = s3.substr(6, 5);  // "world"

    // 比较
    if (s1 == "hello") { ... }

    return 0;
}

#include <iostream>
#include <string>
using namespace std;

int naiveSearch(const string& text, const string& pattern) {
    int n = text.length();
    int m = pattern.length();
    for (int i = 0; i <= n - m; i++) {
        int j;
        for (j = 0; j < m; j++) {
            if (text[i + j] != pattern[j]) break;
        }
        if (j == m) return i;  // 完全匹配
    }
    return -1;  // 未找到
}

int main() {
    string text = "hello world, this is a simple string.";
    string pattern = "world";
    int pos = naiveSearch(text, pattern);
    if (pos != -1) cout << "找到，位置：" << pos << endl;
    else cout << "未找到" << endl;
    return 0;
}

#include <iostream>
#include <string>
#include <vector>
using namespace std;

vector<int> buildNext(const string& pattern) {
    int m = pattern.length();
    vector<int> next(m + 1, 0);  // next[j] 表示当第j位失配时，j应该回退到的位置
    next[0] = -1;
    int i = 0, j = -1;
    while (i < m) {
        if (j == -1 || pattern[i] == pattern[j]) {
            i++; j++;
            next[i] = j;
        } else {
            j = next[j];
        }
    }
    return next;
}

int kmpSearch(const string& text, const string& pattern) {
    vector<int> next = buildNext(pattern);
    int n = text.length(), m = pattern.length();
    int i = 0, j = 0;
    while (i < n && j < m) {
        if (j == -1 || text[i] == pattern[j]) {
            i++; j++;
        } else {
            j = next[j];
        }
    }
    if (j == m) return i - m;
    return -1;
}

int main() {
    string text = "ababcabcabababd";
    string pattern = "ababd";
    int pos = kmpSearch(text, pattern);
    cout << "找到位置：" << pos << endl;  // 输出10
    return 0;
}

hash = (a * base^2 + b * base^1 + c * base^0) % MOD

h[i] = (h[i-1] * base + s[i]) % MOD

hash(l, r) = h[r] - h[l-1] * base^(r-l+1)   (可能需要调整取模)

#include <iostream>
#include <string>
#include <vector>
using namespace std;

typedef unsigned long long ULL;
const int BASE = 131;  // 常用基数
const int MOD = 1e9+7;

ULL pow_base[1000005];  // 预计算 base 的幂

void initPow(int n) {
    pow_base[0] = 1;
    for (int i = 1; i <= n; i++) {
        pow_base[i] = pow_base[i-1] * BASE % MOD;
    }
}

vector<ULL> buildHash(const string& s) {
    int n = s.length();
    vector<ULL> h(n+1, 0);
    for (int i = 1; i <= n; i++) {
        h[i] = (h[i-1] * BASE + s[i-1]) % MOD;
    }
    return h;
}

ULL getHash(const vector<ULL>& h, int l, int r) {
    // l, r 从0开始，子串 s[l..r]
    return (h[r+1] - h[l] * pow_base[r-l+1] % MOD + MOD) % MOD;
}

int main() {
    string s = "hello world";
    initPow(s.length());
    auto h = buildHash(s);
    // 比较 "hello" 和 "world" 是否相等
    ULL hash1 = getHash(h, 0, 4);
    ULL hash2 = getHash(h, 6, 10);
    if (hash1 == hash2) cout << "相等" << endl;
    else cout << "不相等" << endl;
    return 0;
}

#include <iostream>
#include <string>
using namespace std;

const int MAXN = 100005;  // 假设最多这么多节点
int trie[MAXN][26];       // 每个节点有26个字母的指针
int cnt[MAXN];            // 以该节点结尾的单词个数
int nodeCount = 1;        // 根节点编号为0，下一个节点编号从1开始

void insert(const string& word) {
    int p = 0;
    for (char ch : word) {
        int id = ch - 'a';
        if (trie[p][id] == 0) {
            trie[p][id] = nodeCount++;
        }
        p = trie[p][id];
    }
    cnt[p]++;  // 标记单词结尾
}

bool search(const string& word) {
    int p = 0;
    for (char ch : word) {
        int id = ch - 'a';
        if (trie[p][id] == 0) return false;
        p = trie[p][id];
    }
    return cnt[p] > 0;
}

int main() {
    insert("hello");
    insert("world");
    insert("hi");
    cout << search("hello") << endl;  // 1
    cout << search("hell") << endl;   // 0
    return 0;
}

#include <iostream>
#include <string>
#include <unordered_set>
using namespace std;

int lengthOfLongestSubstring(string s) {
    unordered_set<char> window;
    int left = 0, maxLen = 0;
    for (int right = 0; right < s.length(); right++) {
        while (window.count(s[right])) {
            window.erase(s[left]);
            left++;
        }
        window.insert(s[right]);
        maxLen = max(maxLen, right - left + 1);
    }
    return maxLen;
}

int main() {
    string s = "abcabcbb";
    cout << "最长无重复子串长度：" << lengthOfLongestSubstring(s) << endl; // 3 ("abc")
    return 0;
}

// 在Trie节点中增加一个pass统计经过该节点的次数
int pass[MAXN] = {0};

void insert(const string& word) {
    int p = 0;
    pass[p]++;
    for (char ch : word) {
        int id = ch - 'a';
        if (trie[p][id] == 0) trie[p][id] = nodeCount++;
        p = trie[p][id];
        pass[p]++;
    }
    cnt[p]++;
}

int countPrefix(const string& prefix) {
    int p = 0;
    for (char ch : prefix) {
        int id = ch - 'a';
        if (trie[p][id] == 0) return 0;
        p = trie[p][id];
    }
    return pass[p];  // 经过该节点的单词数就是以prefix为前缀的单词数
}