微博通用爬虫代码开源分享

import time
from selenium import webdriver
from selenium.webdriver.common.by import By

local_time = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime())
key_word = input("Please enter your key words:")
number = int(input("Number:"))
url = f"https://m.weibo.cn/search?containerid=100103type%3D1%26q%3D{key_word}"
options = webdriver.ChromeOptions()
options.add_argument('--headless')
driver = webdriver.Chrome(options=options)
driver.get(url)
time.sleep(3)
js = "window.scrollBy(0,800)"  # 向下滑动500个像素  传入x,y坐标
driver.execute_script(js)
time.sleep(1)
for i in range(3, 14, 1):
    try:
        driver.execute_script("window.scrollBy(0,800)")
        time.sleep(0.1)
        media_name = driver.find_element(By.XPATH,
                                         f"//*[@id='app']/div[1]/div[1]/div[{i}]/div/div/div/header/div/div/a/h3").get_attribute(
            "textContent")
        # // *[ @ id = "app"] / div[1] / div[1] / div[3] / div / div / div / header / div / div / a / h3
        # //*[@id="app"]/div[1]/div[1]/div[4]/div/div/div/header/div/div/a/h3
        # //*[@id="app"]/div[1]/div[1]/div[12]/div/div/div/header/div/div/a/h3
        # //*[@id="app"]/div[1]/div[1]/div[13]/div/div/div[1]/div/div/div/header/div/div/a/h3
        element_content = driver.find_element(By.XPATH,
                                              f"//*[@id='app']/div[1]/div[1]/div[{i}]/div/div/div/article/div[2]/div[1]")
        # //*[@id="app"]/div[1]/div[1]/div[3]/div/div/div/article/div[2]/div[1]
        # //*[@id="app"]/div[1]/div[1]/div[12]/div/div/div/article/div[2]/div[1]
        content = element_content.get_attribute("textContent")
        print("------------------------------------------------------------------------------------")
        print(i - 2, "博主昵称：", media_name, "微博内容", content)
        with open("%s.txt" % key_word, "a") as file:
            file.write(content + "\n")
    except Exception as e:
        pass
for i in range(14, number + 4, 1):
    try:
        driver.execute_script("window.scrollBy(0,800)")
        time.sleep(0.1)
        media_name_element = driver.find_element(By.XPATH,
                                                 f"//*
*****************************************************************************************
想要使用后续代码内容请打开咸鱼链接购买代码：【闲鱼】https://m.tb.cn/h.5iteorv?tk=jP8lWXupKJK CZ3457 「我在闲鱼发布了【Python微博爬虫代码分享，以下是一些示例，我搜过微博关键】」
点击链接直接打开

注：需要自己提前配置谷歌的driver驱动到计算机环境变量，大家自行查找线上教程

提示词：输入你需要了解的话题关键词，之后输入你要爬取微博的条数，之后等待片刻，代码将开始爬取数据

如下是我的一个示例截图：

需要完整源码的伙伴可以扫码关注咸鱼购买