如何获取爬取iconfont里面的图标？

Question

如何获取爬取iconfont里面的图标？

iconfont网站的搜索接口是https://www.iconfont.cn/api/icon/search.json，为什么按照接口传递了数据，请求携带的参数:

一直返回的是：Redirecting to /.

应该如何操作呢？才能拿到搜索的数据？

Answer 1

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import os
import re
import time

# 创建保存图标的文件夹
if not os.path.exists('iconfont_icons'):
    os.makedirs('iconfont_icons')

# 设置Chrome选项
chrome_options = Options()
# 如果需要无头模式（不显示浏览器窗口）取消下面这行的注释
# chrome_options.add_argument("--headless")
chrome_options.add_argument("--disable-gpu")
chrome_options.add_argument("--no-sandbox")
chrome_options.add_argument("--disable-dev-shm-usage")
chrome_options.add_argument("--window-size=1920,1080")
chrome_options.add_argument("--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36")

# 初始化WebDriver (需要确保Chrome WebDriver已安装并在PATH中)
driver = webdriver.Chrome(options=chrome_options)

try:
    # 打开网页
    driver.get('https://www.iconfont.cn/collections/detail?spm=a313x.7781069.1998910419.d9df05512&cid=xxxx')

    # 等待页面加载 (最多等待20秒)
    wait = WebDriverWait(driver, 20)
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, 'li[class*="J_icon_id_"]')))

    # 查找所有图标元素
    icon_elements = driver.find_elements(By.CSS_SELECTOR, 'li[class*="J_icon_id_"]')
    print(f"找到 {len(icon_elements)} 个图标")

    # 遍历并保存图标
    for index, icon in enumerate(icon_elements):
        try:
            # 获取SVG元素
            svg_element = icon.find_element(By.CSS_SELECTOR, 'svg')

            # 获取图标名称
            try:
                icon_name_element = icon.find_element(By.CSS_SELECTOR, '.icon-name')
                icon_name = icon_name_element.text.strip()
                filename = f"{icon_name}.svg"
            except:
                # 从元素class中提取ID
                icon_class = icon.get_attribute('class')
                match = re.search(r'J_icon_id_(\d+)', icon_class)
                if match:
                    icon_id = match.group(1)
                    filename = f"icon_{icon_id}.svg"
                else:
                    filename = f"icon_{index}.svg"

            # 清理文件名中的非法字符
            filename = re.sub(r'[\\/*?:"<>|]', "", filename)

            # 获取SVG代码
            svg_html = svg_element.get_attribute('outerHTML')

            # 保存SVG
            with open(os.path.join('iconfont_icons', filename), 'w', encoding='utf-8') as f:
                f.write(svg_html)

            print(f"已保存: {filename}")

            # 添加延迟
            time.sleep(0.5)
        except Exception as e:
            print(f"处理第 {index} 个图标时出错: {e}")

    print('图标爬取完成!')

except Exception as e:
    print(f"爬取过程中出错: {e}")

finally:
    # 关闭浏览器
    driver.quit()

将 xxxx 替换为 cid