利用python+selenium 自动刷新博客访问次数

95 阅读 0 评论 63 点赞

我是靠谱客的博主单纯缘分，这篇文章主要介绍利用python+selenium 自动刷新博客访问次数，现在分享给大家，希望可以做个参考。

以csdn博客为例，目前默认刷新第一页的所有博客文章，可根据css定位规则进行具体修改，例如只访问置顶博客，或者进行连续翻页查询刷新所有博客文章。

本文所采用的两种方式：
1.前台模式：打开浏览器，可以直观看到刷新浏览器刷新，函数功能以_f结尾。
2.后台模式：后台执行，不可见，函数功能以_b结尾。

复制代码

# -*-coding:GBK -*-
from selenium import webdriver
from time import sleep

def init_chrome_f():
    browser = webdriver.Chrome()
    sleep(3)
    print("init chrome by foreground mode !")
    return browser

def init_chrome_b():
    option = webdriver.ChromeOptions()
    option.add_argument("headless")
    browser = webdriver.Chrome(options=option)
    sleep(3)
    print("init chrome by background mode !")
    return browser

def refresh_blog(browser, loop_count):
    # 获取当前打开的所有句柄
    all_handles = browser.window_handles
    # 循环刷新已经打开的句柄
    for loop in range(loop_count):
        print("loop_count: ", loop+1)
        for tmp_handle in all_handles:
            browser.switch_to.window(tmp_handle)
            browser.refresh()
            print("refreshing handle :", tmp_handle)
            sleep(3)

def visit_blog_f(browser, link_list, loop_count=100):
    for index in range(len(link_list)):
        # 获取文本内容
        # out_html = ret[index].get_attribute('outerHTML')
        # 点击打开博客链接
        link_list[index].click()
        sleep(5)
        # link = tmp_link.get_attribute("href")
        # print("link_href:", link)
    refresh_blog(browser, loop_count)

def visit_blog_b(browser, link_list, loop_count=100):
    # 以后台的方式访问博客
    for index in link_list:
        tmp_url = index.get_attribute("href")
        js = f"window.open('{tmp_url}');"
        browser.execute_script(js)
        print("js open tmp_link :", tmp_url)
        sleep(3)
    refresh_blog(browser, loop_count)

def get_all_blog_links(browser, blog_url):
    # 在当前浏览器中访问blog_url
    browser.get(blog_url)
    sleep(3)
    link_list = browser.find_elements_by_css_selector(r".article-list>.article-item-box>h4>a[href]")
    # print(ret)
    return link_list

def main_f():
    blog_url = r"https://blog.csdn.net/zhang1308299607"
    browser = init_chrome_f()
    link_list = get_all_blog_links(browser, blog_url)
    visit_blog_f(browser, link_list, loop_count=100)
    browser.quit()

def main_b():
    blog_url = r"https://blog.csdn.net/zhang1308299607"
    browser = init_chrome_b()
    link_list = get_all_blog_links(browser, blog_url)
    visit_blog_b(browser, link_list, loop_count=100)
    browser.quit()

if __name__ == "__main__":
    # main_f()
    main_b()
    # input("please press <enter> to exit!")

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
# -*-coding:GBK -*-
from selenium import webdriver
from time import sleep


def init_chrome_f():
    browser = webdriver.Chrome()
    sleep(3)
    print("init chrome by foreground mode !")
    return browser


def init_chrome_b():
    option = webdriver.ChromeOptions()
    option.add_argument("headless")
    browser = webdriver.Chrome(options=option)
    sleep(3)
    print("init chrome by background mode !")
    return browser


def refresh_blog(browser, loop_count):
    # 获取当前打开的所有句柄
    all_handles = browser.window_handles
    # 循环刷新已经打开的句柄
    for loop in range(loop_count):
        print("loop_count: ", loop+1)
        for tmp_handle in all_handles:
            browser.switch_to.window(tmp_handle)
            browser.refresh()
            print("refreshing handle :", tmp_handle)
            sleep(3)


def visit_blog_f(browser, link_list, loop_count=100):
    for index in range(len(link_list)):
        # 获取文本内容
        # out_html = ret[index].get_attribute('outerHTML')
        # 点击打开博客链接
        link_list[index].click()
        sleep(5)
        # link = tmp_link.get_attribute("href")
        # print("link_href:", link)
    refresh_blog(browser, loop_count)


def visit_blog_b(browser, link_list, loop_count=100):
    # 以后台的方式访问博客
    for index in link_list:
        tmp_url = index.get_attribute("href")
        js = f"window.open('{tmp_url}');"
        browser.execute_script(js)
        print("js open tmp_link :", tmp_url)
        sleep(3)
    refresh_blog(browser, loop_count)


def get_all_blog_links(browser, blog_url):
    # 在当前浏览器中访问blog_url
    browser.get(blog_url)
    sleep(3)
    link_list = browser.find_elements_by_css_selector(r".article-list>.article-item-box>h4>a[href]")
    # print(ret)
    return link_list


def main_f():
    blog_url = r"https://blog.csdn.net/zhang1308299607"
    browser = init_chrome_f()
    link_list = get_all_blog_links(browser, blog_url)
    visit_blog_f(browser, link_list, loop_count=100)
    browser.quit()


def main_b():
    blog_url = r"https://blog.csdn.net/zhang1308299607"
    browser = init_chrome_b()
    link_list = get_all_blog_links(browser, blog_url)
    visit_blog_b(browser, link_list, loop_count=100)
    browser.quit()


if __name__ == "__main__":
    # main_f()
    main_b()
    # input("please press <enter> to exit!")