使用python利用第三方登录实现自动化简书发布文章

发表于 |

话不多说 首先附上代码

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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
import time

from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait

import re

import linecache


class Main(object):
    # init
    def __init__(self, file):
        self.title = ''
        self.content = ''
        self.category = ''
        self.tags = ''
        # OsChina的系统分类, 设个默认值
        self.osChina_sys_category = '编程语言'
        # CSDN的文章分类, 设个默认值
        self.csdn_article_category = '原创'
        # CSDN的博客分类, 设个默认值
        self.csdn_blog_category = '后端'
        self.read_file(file)

    # 读取MD中的title, content, self_category, self_tags, osChina_sys_category, csdn_article_category, csdn_blog_category
    def read_file(self, markdown_file):
        self.title = linecache.getline(markdown_file, 2).split('title: ')[1].strip('\n')
        with open(markdown_file, 'r', encoding='UTF-8') as f:
            self.content = f.read().split('-->\n')[1]
            # 重置文件指针偏移量
            f.seek(0)
            for line in f.readlines():
                if re.search('self_category: ', line) is not None:
                    self.category = line.split('self_category: ')[1].strip('\n')
                elif re.search('self_tags: ', line) is not None:
                    self.tags = line.split('self_tags: ')[1].strip('\n')
                elif re.search('osChina_sys_category: ', line) is not None:
                    self.osChina_sys_category = line.split('osChina_sys_category: ')[1].strip('\n')
                elif re.search('csdn_article_category: ', line) is not None:
                    self.csdn_article_category = line.split('csdn_article_category: ')[1].strip('\n')
                elif re.search('csdn_blog_category: ', line) is not None:
                    self.csdn_blog_category = line.split('csdn_blog_category: ')[1].strip('\n')




# QQ授权登录, 使用前提是QQ客户端在线
def qq(driver, timeout):
    # 切换到最新打开的窗口
    window_handles = driver.window_handles
    driver.switch_to.window(window_handles[-1])

    print('qq authorize title is ', driver.title)

    # 切换iframe
    iframe = WebDriverWait(driver, timeout).until(lambda d: d.find_element_by_id('ptlogin_iframe'))
    driver.switch_to.frame(iframe)

    # 点击头像进行授权登录
    login = WebDriverWait(driver, timeout).until(lambda d: d.find_element_by_xpath('//*[@id="qlogin_list"]/a[1]'))
    login.click()
# 简书
class JianShu(object):
    @staticmethod
    def post(main, timeout, self_timeout=3):
        # 1.跳转登陆
        login = 'https://www.jianshu.com/sign_in'
        driver = webdriver.Chrome()
        driver.get(login)

        # 2.窗口最大化
        driver.maximize_window()

        # 3.使用QQ授权登录
        driver.find_element_by_xpath('/html/body/div[1]/div[2]/div/div/ul/li[3]/a/i').click()
        driver.close()
        qq(driver, timeout)

        # 4.点击"写文章"
        write_blog = WebDriverWait(driver, timeout).until(lambda d: d.find_element_by_xpath('/html/body/nav/div/a[2]'))
        write_blog = WebDriverWait(driver, timeout).until(lambda d: d.find_elements_by_class_name('/html/body/nav/div/a[2]'))
        write_blog.click()
        driver.close()
        time.sleep(3)
       # window_handles = driver.window_handles
        #driver.switch_to.window(window_handles[-1])

        # 5.点击指定分类
        classify = WebDriverWait(driver, timeout).until(lambda d: d.find_elements_by_class_name('_3DM7w'))
        for c in classify:
            html = c.get_attribute('innerHTML')
            if main.category in html:
                c.click()
            else:
                # TODO 如果分类不存在，还可以直接新建分类
                pass

        # 6.点击'新建文章'
        time.sleep(self_timeout)
        new_article = WebDriverWait(driver, timeout).until(
            lambda d: d.find_element_by_xpath('//*[@id="root"]/div/div[2]/div[1]/div/div/div/div[1]/i'))
        new_article.click()
        article = WebDriverWait(driver, timeout).until(
            lambda d: d.find_element_by_xpath('//*[@id="root"]/div/div[2]/div[1]/div/div/div/ul/li[1]'))
        article.click()

        # 7.填写标题, 内容
        time.sleep(self_timeout)
        title = driver.find_element_by_class_name('_24i7u')
        title.clear()
        title.send_keys(main.title)
        content = driver.find_element_by_id('arthur-editor')
        content.clear()
        content.send_keys(main.content)

        # 8.保存草稿
        driver.find_element_by_xpath('//*[@id="root"]/div/div[2]/div[2]/div/div/div/div/ul/li[8]/a').click()
        # 8.发布文章
        # driver.find_element_by_xpath('//*[@id="root"]/div/div[2]/div[2]/div/div/div/div/ul/li[1]/a').click()


if __name__ == '__main__':
    md_file = 'auto.md'
    print("Markdown File is ", md_file)

    timeout = 30
    main = Main(md_file)

    # 简书
    jian_shu = JianShu()
    jian_shu.post(main, timeout)

PS：Selenium操纵浏览器是依赖于浏览器驱动程序的，不同版本的浏览器需要下载不同版本的驱动, 否则程序无法运行, 下面贴出的是谷歌和火狐浏览器驱动程序的下载地址。

Chrome ( chromedriver ) Firefox ( geckodriver )
官方下载 官方下载
淘宝镜像 淘宝镜像
备用下载 备用下载

关于谷歌驱动的下载安装, 详情可参见文章《Web自动化框架selenium的介绍与使用》

本文为作者原创 转载时请注明出处 谢谢

乱码三千 – 点滴积累 ,欢迎来到乱码三千技术博客站

0%