import re import json import time import requests import datetime import pymysql import selenium from bs4 import BeautifulSoup from selenium import webdriver from selenium.webdriver.support.ui import WebDriverWait from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime from sqlalchemy.orm import sessionmaker from sqlalchemy.ext.declarative import declarative_base from selenium.webdriver import Edge, EdgeOptions # 创建浏览器对象 options = EdgeOptions() options.use_chromium = True options.binary_location = r'C:\Users\邓枫林\PycharmProjects\pythonProject\edgedriver_win64\msedgedriver.exe' browser = Edge(options=options) wait = WebDriverWait(browser, 10) # 打开微博话题页面 url = 'https://weibo.com/n/%E4%B8%AD%E5%9B%BD%E9%A3%9F%E5%93%81%E5%8D%AB%E7%94%9F?from=feed&loc=at&nick=%E4%B8%AD%E5%9B%BD%E9%A3%9F%E5%93%81%E5%8D%AB%E7%94%9F&order=hot' browser.get(url) # 等待页面加载完成 wait.until(lambda driver: driver.execute_script("return document.readyState") == "complete") browser = selenium.webdriver.Edge(executable_path='C:/Users/邓枫林/PycharmProjects/pythonProject/edgedriver_win64/msedgedriver.exe') wait = selenium.webdriver.support.ui.WebDriverWait(browser, 10) # 监测页面是否包含“高校类”敏感词汇 if '高校类' in browser.page_source: # 获取原始微博 weibo = browser.find_element_by_css_selector('.WB_feed_detail .WB_text.W_f14').text # 获取转发该微博的用户昵称和转发内容 reposts = [] repost_items = browser.find_elements_by_css_selector('.list_ul .list_li') for item in repost_items: nickname = item.find_element_by_css_selector('.WB_text.W_f14').text content = item.find_element_by_css_selector('.WB_text.W_f14 + .comment_txt').text reposts.append({'nickname': nickname, 'content': content}) # 关闭浏览器 browser.quit() # 将微博和转发内容存入MySQL数据库中 Base = declarative_base() class Weibo(Base): __tablename__ = 'weibo_user' id = Column(Integer, primary_key=True) content = Column(Text) create_time = Column(DateTime) class Repost(Base): __tablename__ = 'weibo_repost' id = Column(Integer, primary_key=True) weibo_id = Column(Integer) nickname = Column(String(50)) content = Column(Text) engine = create_engine('mysql+pymysql://root:root@hostname:port/weibo?charset=utf8mb4') Session = sessionmaker(bind=engine) session = Session() now = datetime.datetime.now() weibo_obj = Weibo(content=weibo, create_time=now) session.add(weibo_obj) session.commit() for repost in reposts: repost_obj = Repost(weibo_id=weibo_obj.id, nickname=repost['nickname'], content=repost['content']) session.add(repost_obj) session.commit() session.close() else: # 关闭浏览器 browser.quit()

这是一个使用 Selenium 和 Python 进行微博爬虫的代码，通过打开指定的微博话题页面，判断页面是否包含“高校类”敏感词汇，如果包含敏感词汇，则获取原始微博和转发该微博的用户昵称和转发内容，并将这些信息存入 MySQL 数据库中。如果不包含敏感词汇，则直接关闭浏览器。在使用代码前，需要安装相关的 Python 库以及浏览器驱动程序，并且要将代码中的数据库连接信息修改为自己的信息。需要注意的是，爬虫行为需要遵守相关法律法规和网站的规定，不得用于非法用途。

相关问题

import requests from bs4 import BeautifulSoup import pymysql import random from selenium import webdriver from selenium.webdriver import ChromeOptions import re import time import requests

这段代码有一个语法错误，应该在 import 语句之间加上换行符。正确的写法如下：

import requests 
from bs4 import BeautifulSoup 
import pymysql 
import random 
from selenium import webdriver 
from selenium.webdriver import ChromeOptions 
import re 
import time 

import requests

import re import json import time import requests import datetime import pymysql import selenium from bs4 import BeautifulSoup from selenium import webdriver from selenium.webdriver.support.ui import WebDriverWait from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime from sqlalchemy.orm import sessionmaker from sqlalchemy.ext.declarative import declarative_base from selenium.webdriver import Edge, EdgeOptions # 创建浏览器对象 options = EdgeOptions() options.use_chromium = True options.binary_location = r'C:\Users\邓枫林\PycharmProjects\pythonProject\edgedriver_win64\msedgedriver.exe' browser = Edge(options=options) wait = WebDriverWait(browser, 10) # 打开微博话题页面 url = 'https://weibo.com/n/%E4%B8%AD%E5%9B%BD%E9%A3%9F%E5%93%81%E5%8D%AB%E7%94%9F?from=feed&loc=at&nick=%E4%B8%AD%E5%9B%BD%E9%A3%9F%E5%93%81%E5%8D%AB%E7%94%9F&order=hot' browser.get(url) # 等待页面加载完成 wait.until(lambda driver: driver.execute_script("return document.readyState") == "complete") browser = selenium.webdriver.Edge(executable_path='C:/Users/邓枫林/PycharmProjects/pythonProject/edgedriver_win64/msedgedriver.exe') wait = selenium.webdriver.support.ui.WebDriverWait(browser, 10) # 监测页面是否包含“高校类”敏感词汇 if '高校类' in browser.page_source: # 获取原始微博 weibo = browser.find_element_by_css_selector('.WB_feed_detail .WB_text.W_f14').text # 获取转发该微博的用户昵称和转发内容 reposts = [] repost_items = browser.find_elements_by_css_selector('.list_ul .list_li') for item in repost_items: nickname = item.find_element_by_css_selector('.WB_text.W_f14').text content = item.find_element_by_css_selector('.WB_text.W_f14 + .comment_txt').text reposts.append({'nickname': nickname, 'content': content}) # 关闭浏览器 browser.quit() # 将微博和转发内容存入MySQL数据库中 Base = declarative_base() class Weibo(Base): tablename = 'weibo_user' id = Column(Integer, primary_key=True) content = Column(Text) create_time = Column(DateTime) class Repost(Base): tablename = 'weibo_repost' id = Column(Integer, primary_key=True) weibo_id = Column(Integer) nickname = Column(String(50)) content = Column(Text) engine = create_engine('mysql+pymysql://root:root@hostname:port/weibo?charset=utf8mb4') Session = sessionmaker(bind=engine) session = Session() now = datetime.datetime.now() weibo_obj = Weibo(content=weibo, create_time=now) session.add(weibo_obj) session.commit() for repost in reposts: repost_obj = Repost(weibo_id=weibo_obj.id, nickname=repost['nickname'], content=repost['content']) session.add(repost_obj) session.commit() session.close() else: # 关闭浏览器 browser.quit()

这段代码是一个 Python 程序，使用了 Selenium 库模拟浏览器行为，从微博话题页面中获取微博和转发内容，并将它们存入 MySQL 数据库中。其中，程序打开了一个 Microsoft Edge 浏览器对象，等待页面加载完成后进行操作。如果页面包含“高校类”敏感词汇，则获取微博和转发内容，并将它们存入数据库。如果页面不包含该敏感词汇，则直接关闭浏览器。