<?php
// 数据库连接信息
$host = 'localhost'; // 或者是数据库服务器的IP地址
$dbname = 'your_database_name'; // 替换为你的数据库名
$username = 'your_username'; // 替换为你的数据库用户名
$password = 'your_password'; // 替换为你的数据库密码

// 创建连接
$conn = new mysqli($host, $username, $password, $dbname);

// 检查连接
if ($conn->connect_error) {
    die("连接失败: " . $conn->connect_error);
}

// 查询示例
$sql = "SELECT * FROM job_post WHERE title LIKE '%软件工程师%'";
$result = $conn->query($sql);

if ($result->num_rows > 0) {
    // 输出数据
    while($row = $result->fetch_assoc()) {
        echo "id: " . $row["id"]. " - Title: " . $row["title"]. "<br>";
    }
} else {
    echo "0 结果";
}

// 关闭连接
$conn->close();
?>

import requests

# 代理服务器(根据实际情况修改)
proxy = {
    'http': 'http://12.34.56.78:8080',
    'https': 'https://12.34.56.78:8080'
}

# 目标网页(根据实际需求修改)
url = 'http://example.com'

# 发送请求
response = requests.get(url, proxies=proxy)

# 输出抓取结果
print(response.text)

import requests

def download_image(url, file_path):
    response = requests.get(url)
    if response.status_code == 200:
        with open(file_path, 'wb') as file:
            file.write(response.content)
        print(f"Image saved to: {file_path}")
    else:
        print(f"Failed to download image: {response.status_code}")

# 使用示例
image_url = "http://example.com/image.jpg"
save_path = "downloaded_image.jpg"
download_image(image_url, save_path)

import requests
from bs4 import BeautifulSoup
import threading

def get_content(url, session):
    response = session.get(url)
    if response.status_code == 200:
        return response.text
    return None

def parse_content(content, url):
    soup = BeautifulSoup(content, 'html.parser')
    # 解析内容，提取有价值信息
    print(f'Parsed content from {url}')

def main():
    # 初始化一个Session对象，以便复用连接
    with requests.Session() as session:
        # 创建线程列表
        threads = []
        # 假设我们有一个urls列表，包含我们要爬取的网页
        urls = [...]

        for url in urls:
            # 为每个url创建一个线程
            t = threading.Thread(target=get_content, args=(url, session))
            t.start()
            threads.append(t)

        for thread in threads:
            thread.join()  # 等待所有线程完成

if __name__ == '__main__':
    main()

import requests
from bs4 import BeautifulSoup

def get_page_title(url):
    response = requests.get(url)
    if response.status_code == 200:
        soup = BeautifulSoup(response.text, 'html.parser')
        return soup.title.string
    else:
        return "Error: Page not found or the request was not successful"

url = "http://example.com"  # 替换为你想爬取的网页
title = get_page_title(url)
print(title)

import requests
from pyquery import PyQuery as pq

# 知乎登录URL
login_url = 'https://www.zhihu.com/login/phone_num'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
    'Referer': 'https://www.zhihu.com/signin?next=%2F'
}

# 登录函数
def login(session, username, password):
    # 获取登录时需要的_xsrf参数
    home_page = session.get('https://www.zhihu.com/', headers=headers)
    home_page.encoding = 'utf-8'
    doc = pq(home_page.text)
    _xsrf = doc('#signin-xsrf').attr('value')

    # 发送登录请求
    data = {
        '_xsrf': _xsrf,
        'phone_num': username,
        'password': password
    }
    session.post(login_url, headers=headers, data=data)

# 初始化session
session = requests.Session()

# 用户名和密码
username = 'your_phone_number'
password = 'your_password'

# 登录
login(session, username, password)

# 要爬取的用户的id
user_id = 'your_target_user_id'

# 获取用户主页
user_home_page = session.get('https://www.zhihu.com/people/' + user_id, headers=headers)
user_home_page.encoding = 'utf-8'

# 使用pyquery解析页面
doc = pq(user_home_page.text)
author_info = doc('.author-info-wrap').text()
print(author_info)

# 以下可以继续根据需要爬取用户的关注列表、回答、文章等信息

import requests
from bs4 import BeautifulSoup

url = 'http://example.com/comments'
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
comments = soup.find_all('div', class_='comment')

import jieba
from wordcloud import WordCloud

text = " ".join(comments)
cut_text = " ".join(jieba.cut(text))
wordcloud = WordCloud(font_path='simhei.ttf').generate(cut_text)

from sklearn.cluster import KMeans

data = [vectorize_comments(comment) for comment in comments]
kmeans = KMeans(n_clusters=4)
kmeans.fit(data)

from sklearn.decomposition import LatentDirichletAllocation

X = vectorize_comments(comments)
lda = LatentDirichletAllocation(n_topics=3, random_state=1)
lda.fit(X)

import networkx as nx

graph = nx.Graph()
for comment in comments:
    graph.add_edge(comment.user_id, comment.reply_user_id)

import requests
from bs4 import BeautifulSoup

def get_html(url):
    """发送HTTP请求，获取网页HTML内容"""
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        else:
            return None
    except requests.RequestException:
        return None

def parse_html(html):
    """解析HTML，提取有效信息"""
    soup = BeautifulSoup(html, 'html.parser')
    # 假设我们要提取所有的段落文本
    paragraphs = soup.find_all('p')
    return [p.get_text() for p in paragraphs]

def main():
    url = 'http://example.com'  # 替换为你想爬取的网页URL
    html = get_html(url)
    if html:
        parsed_data = parse_html(html)
        for data in parsed_data:
            print(data)
    else:
        print("Failed to retrieve the webpage")

if __name__ == '__main__':
    main()

import requests
from fake_useragent import UserAgent

def download_page(url, proxy=None):
    # 生成随机的User-Agent
    ua = UserAgent()
    headers = {'User-Agent': ua.random}

    try:
        if proxy:
            response = requests.get(url, headers=headers, proxies=proxy)
        else:
            response = requests.get(url, headers=headers)

        if response.status_code == 200:
            return response.text
        else:
            return "Error downloading the page"
    except requests.exceptions.RequestException:
        return "Error downloading the page"

# 使用时，可以传入代理服务器地址，例如:
# proxy = {'http': 'http://123.123.123.123:8080', 'https': 'https://123.123.123.123:8080'}
# content = download_page('https://example.com', proxy)

import random
import time

import scrapy

class MySpider(scrapy.Spider):
    name = 'myspider'
    start_urls = ['http://example.com/']

    # 代理列表
    proxy_list = [
        'http://proxy1.com',
        'http://proxy2.com',
        # ...
    ]

    def start_requests(self):
        # 随机选择一个代理并发送请求
        proxy = random.choice(self.proxy_list)
        for url in self.start_urls:
            yield scrapy.Request(url, self.parse, meta={'proxy': proxy})

    def parse(self, response):
        # 实现对请求频率的限制
        delay = 1.0 / self.rps_limit  # 例如，每秒请求数（RPS）限制为1
        time.sleep(delay)

        # 爬取逻辑...