python完整自动化爬虫+数据分析+绘图项目案例

import csv from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.chrome.service import Service import time chrome_driver_path = r"D:\chromedriver.exe" driver = webdriver.Chrome(service=Service(chrome_driver_path)) url = "https://www.shanghairanking.cn/rankings/bcur/2024" driver.get(url) name_list = [] provinces_list = [] types_list = [] scores_list = [] # driver.maximize_window() for i in range(20): names = driver.find_elements(By.CSS_SELECTOR, "span[data-v-2b687c30].name-cn") for element in names: text_content = element.text name_list.append(text_content) provinces = driver.find_elements(By.CSS_SELECTOR, "td[data-v-389300f0]:nth-child(3)") for element in provinces: text_content = element.text provinces_list.append(text_content) types = driver.find_elements(By.CSS_SELECTOR, "td[data-v-389300f0]:nth-child(4)") for element in types: text_content = element.text types_list.append(text_content) scores = driver.find_elements(By.CSS_SELECTOR, "td[data-v-389300f0]:nth-child(5)") for element in scores: text_content = element.text scores_list.append(text_content) next_page_button = driver.find_element(By.CSS_SELECTOR, "svg[data-icon='right']") next_page_button.click() time.sleep(0.2) # for n, p, t, s in zip(name_list, provinces_list, types_list, scores_list): # print(f"学校名：{n} 所在省市：{p} 类型：{t} 评分：{s}") data = list(zip(name_list, provinces_list, types_list, scores_list)) csv_file_path = "university.csv" headers = ["大学名称", "所在省市", "类型", "评分"] with open(csv_file_path, 'w', newline='', encoding='utf-8') as csvfile: writer = csv.writer(csvfile) writer.writerow(headers) for row in data: writer.writerow(row)