nlcBookCrawler/test2.py at master · peade/nlcBookCrawler · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
import selenium
from selenium import webdriver
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time, os

# import qrcode

browser = webdriver.Chrome()


def user_login():
    browser.get("https://www.xuexi.cn/")
    # login_iframe = browser.find_elements_by_tag_name('iframe')[-2]
    # browser.switch_to.frame(login_iframe)
    # qr_element = browser.find_element_by_css_selector("#qrcode img")
    # browser.execute_script("arguments[0].scrollIntoView();", qr_element)
    print("等待扫码登录")
    # while True:  # FIXME 这里需要用命令行显示qr_str并扫码登录
    #     time.sleep(1)
    #     if "login" not in browser.current_url:
    #         print("登录成功")
    #         return


def read_news():
    browser.get("https://www.xuexi.cn/")
    WebDriverWait(browser, 60).until(EC.presence_of_element_located((By.TAG_NAME, 'div')))
    time.sleep(10)
    news = browser.find_elements_by_css_selector(".text-link-item-title")
    print(len(news))
    cnt = 1
    for element in news[5:15]:  # 读5-15条新闻
        print("开始读第{}条新闻".format(cnt))
        cnt = cnt + 1
        try:
            browser.execute_script("arguments[0].scrollIntoView();", element)
            element.click()
            browser.switch_to.window(browser.window_handles[0])
            browser.switch_to.window(browser.window_handles[-1])
            for _ in range(100):
                ActionChains(browser).key_down(Keys.DOWN).perform()
                time.sleep(0.2)
            browser.close()
            browser.switch_to.window(browser.window_handles[0])
        except selenium.common.exceptions.ElementNotVisibleException as e:
            print(e)
            pass


def watch_video():
    browser.get("https://www.xuexi.cn/")
    browser.find_element_by_link_text("学习电视台").click()

    # 关闭主标签页
    browser.switch_to.window(browser.window_handles[0])
    browser.close()
    browser.switch_to.window(browser.window_handles[0])

    # 切换到"第一频道"
    browser.find_element_by_link_text("第一频道").click()
    # 关闭主标签页
    browser.switch_to.window(browser.window_handles[0])
    browser.close()
    browser.switch_to.window(browser.window_handles[0])

    time.sleep(5)  # 等待js运行完毕
    videos = browser.execute_script('return $("div.word-item")')
    video_flag = False
    cnt = 1
    for video in videos:
        video_flag = not video_flag
        if video_flag:
            print("开始看第{}条视频".format(cnt))
            cnt = cnt + 1
            video.click()
            browser.execute_script("arguments[0].scrollIntoView();",
                                   browser.execute_script('''return $("div:contains('>>')")[5]'''))
            time.sleep(60)
            browser.switch_to.window(browser.window_handles[-1])  # 关闭当前标签页
            browser.close()
            browser.switch_to.window(browser.window_handles[0])


if __name__ == "__main__":
    # user_login()
    read_news()
    # watch_video()