初始爬虫11 - 技术栈

1.斗鱼selenium爬取

python 复制代码

# -*- coding: utf-8 -*-
from selenium import webdriver
from selenium.webdriver.common.by import By
import time

class Douyu(object):
    def __init__(self):
        self.url = 'https://www.douyu.com/directory/all'
        self.driver = webdriver.Chrome()
        self.driver.implicitly_wait(10)  # 设置隐式等待，最大等待10秒

    def parse_data(self):
        room_list = self.driver.find_elements(By.XPATH, '//*[@id="listAll"]/section[2]/div[2]/ul/li/div')
        print(len(room_list))
        data_list = []

        # 遍历房间列表，从每一个房间节点获取数据
        for room in room_list:
            temp = {}
            # temp['title'] = room.find_element(By.XPATH, './div[2]/div[1]/a').text
            # temp['type'] = room.find_element(By.XPATH, './div[2]/div[2]/span/a').text
            # temp['owner'] = room.find_element(By.XPATH, './div[1]/div/a/div/div[2]/div/div[1]/div').text
            # temp['num'] = room.find_element(By.XPATH, './div[1]/div/a/div/div[2]/div/div[2]/span').text
            temp['picture'] = room.find_element(By.XPATH, './div[1]/picture/source[1]').get_attribute('srcset')
            # print(temp)
            data_list.append(temp)
        return data_list


    def run(self):
        self.driver.get(self.url)
        total_rooms = 0
        last_count = 0  # 上一次获取的房间数量
        while True:
            # 滚动到页面底部
            self.driver.execute_script('window.scrollTo(0, document.body.scrollHeight);')
            time.sleep(2)  # 等待页面加载新内容

            # 获取当前房间数据
            new_data = self.parse_data()
            total_rooms += len(new_data)
            print(f"Total rooms : {total_rooms}")

            # 检查当前房间数量
            if total_rooms == last_count:  # 如果新加载的房间数量没有增加，停止滚动
                print("No more new data to load.")
                break
            last_count = total_rooms  # 更新最后一次的房间数量

        print(f"Final total rooms fetched: {total_rooms}")
        self.driver.quit()  # 退出浏览器


if __name__ == '__main__':
    douyu = Douyu()
    douyu.run()

2. request+mysql存储

python 复制代码

import pymysql
import requests
from lxml import etree

# 第一步：请求百度首页并提取内容
url = 'https://www.baidu.com/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36'
}
response = requests.get(url, headers=headers)
html = etree.HTML(response.content.decode("utf-8"))

# 提取文本和链接
classes = ["normal", "c", "color", "t"]
extracted_data = []

for cls in classes:
    xpath_query = f'//div[contains(@class, "{cls}")]'
    elements = html.xpath(xpath_query)
    for element in elements:
        # 提取文本内容
        text = ''.join(element.xpath('.//text()')).strip()
        # 提取链接，假定链接是 a 标签的 href 属性
        link = element.xpath('.//a/@href')
        link = link[0] if link else "No link found"
        extracted_data.append((text, link))

# 第二步：连接 MySQL 数据库
connection = pymysql.connect(
    host='localhost',  # 数据库地址
    user='root',  # MySQL 用户名
    password='991016',  # MySQL 密码
    database='test',  # 数据库名称
    charset='utf8mb4',  # 确保字符集是 utf8mb4
    cursorclass=pymysql.cursors.DictCursor  # 使用字典形式的游标
)

try:
    with connection.cursor() as cursor:
        # 创建一个新表存储网页内容
        create_table_query = """
        CREATE TABLE IF NOT EXISTS web_content (
            id INT AUTO_INCREMENT PRIMARY KEY,
            text_content TEXT,
            link VARCHAR(255)
        );
        """
        cursor.execute(create_table_query)

        # 插入提取到的数据
        insert_query = "INSERT INTO web_content (text_content, link) VALUES (%s, %s)"
        cursor.executemany(insert_query, extracted_data)

        # 提交更改
        connection.commit()

        # 查询数据并验证是否成功存储
        cursor.execute("SELECT * FROM web_content")
        results = cursor.fetchall()
        for row in results:
            print(row)

finally:
    connection.close()