学习强国——中华诗词精典

颂读历史经典，传承文化血脉。

网址：‘https://www.xuexi.cn/4b3be22f3d07308c2ce39e5ca84a499c/13a0b6125672c7157db254071de2c1f0.html’

1.模拟打开网址。

browse.get('https://www.xuexi.cn/4b3be22f3d07308c2ce39e5ca84a499c/13a0b6125672c7157db254071de2c1f0.html')

2.按照历史顺序拆分的各年代板块列表

list0 = browse.find_elements(By.CSS_SELECTOR,'.tab-wrapper.horizontal-item')

3.选定板块，点击“更多”，得到该板块所有内容列表。

如，browse.find_element(By.CSS_SELECTOR,'#f44f div.hotItem').click()  # 点击更多

4.得到文章标题列表。

list_1 = browse.find_elements(By.CSS_SELECTOR, 'div.text-link-item-title')

5.点击文章标题，浏览文章。

dingwei = list_1[i].find_element(By.CSS_SELECTOR, '.text-wrap .text')
title = dingwei.text
dingwei.click()
all_window_handles = browse.window_handles
browse.switch_to.window(all_window_handles[-1])
time.sleep(2)
print(f"诗词内容:", title)
for i in range(1, 60):
    browse.execute_script(f"window.scrollTo(0, document.body.scrollHeight / (60/{i}));")
    time.sleep(1)

6.上代码：

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

browse = webdriver.Edge()
browse.maximize_window()  # 窗口最大化
browse.implicitly_wait(30)

print('版块：中华诗词经典')
browse.get('https://www.xuexi.cn/4b3be22f3d07308c2ce39e5ca84a499c/13a0b6125672c7157db254071de2c1f0.html')
time.sleep(1)
list0 = browse.find_elements(By.CSS_SELECTOR,'.tab-wrapper.horizontal-item')
for item0 in list0:
    print(f'{item0.text}部分：')
    item0.click()
    time.sleep(1)
    browse.find_element(By.CSS_SELECTOR,'#f44f div.hotItem').click()
    time.sleep(1)
    all_window_handles0 = browse.window_handles
    browse.switch_to.window(all_window_handles0[-1])
    page_info = browse.find_element(By.CSS_SELECTOR, 'div._123TewfUWxUbDqs5ecsq6k')
    if page_info:
        list_page = page_info.find_elements(By.CSS_SELECTOR, '.btn')
        page_end = int(list_page[-1].text)
        page = 1
        while page <= page_end:
            list_1 = browse.find_elements(By.CSS_SELECTOR, 'div.text-link-item-title')
            for i in range(len(list_1)):
                dingwei = list_1[i].find_element(By.CSS_SELECTOR, '.text-wrap .text')
                title = dingwei.text
                dingwei.click()
                all_window_handles = browse.window_handles
                browse.switch_to.window(all_window_handles[-1])
                time.sleep(2)
                print(f"诗词内容:", title)
                for i in range(1, 60):
                    browse.execute_script(f"window.scrollTo(0, document.body.scrollHeight / (60/{i}));")
                    time.sleep(1)
                browse.close()
                browse.switch_to.window(all_window_handles[-2])
            page += 1
            list_page = page_info.find_elements(By.CSS_SELECTOR, '.btn')
            for page_ in list_page:
                if page_.text == str(page):
                    page_.click()
                    break
            time.sleep(1)
    browse.close()
    browse.switch_to.window(all_window_handles0[-2])