add code file

data/全程软件测试（第3版）/第02章 全程测试：闪光的思想/2.2 测试驱动开发/code_1.java

+Title (one line describing the story)
+Narrative:
+As a [role]
+I want [feature]
+So that [benefit]
+
+Acceptance criteria: (presented as Scenarios)
+
+Scenario 1: Title
+Given [context]
+  And [some more context]...
+When [event]
+Then [outcome]
+  And [another outcome]...
+
+Scenario 2: ...
\ No newline at end of file

data/全程软件测试（第3版）/第03章 准备：基础设施与TA框架/3.4 自动化测试框架/code_1.java

+public static void main(String[] args) {
+   // 首先创建一个 FireFox 浏览器webdriver的实例，并让浏览器访问必应
+   WebDriver driver = new FirefoxDriver();
+   driver.get("http://cn.bing.com");
+// 获取页面的 title
+   System.out.println("Home Page title: " + driver.getTitle());
+   // 通过id找到input的web UI元素，并在此域内输入“软件测试”,并提交
+   WebElement element = driver.findElement(By.id("sb_form_q"));
+// 或通过xPath来定位web元素
+// element = driver.findElement(By.xpath("*[@id='sb_form_q']"))
+   // 在此域内输入“软件测试”，并提交
+element.sendKeys(“软件测试”);
+  element.submit();
+  // 通过判断 title 内容等待搜索页面加载完毕
+  (new WebDriverWait(driver, 10)).until(new ExpectedCondition() {
+    public Boolean apply(WebDriver d) {
+          return d.getTitle().toLowerCase().endsWith(“软件测试”);
+    }
+  });
+  System.out.println("Result Page title: " + driver.getTitle());
+  driver.quit();
+ }
\ No newline at end of file

data/全程软件测试（第3版）/第03章 准备：基础设施与TA框架/3.4 自动化测试框架/code_2.java

+
+4.0.0　　　　 
+   MySel20Proj　　　　　 
+   MySel20Proj
+1.0
+
+
+org.seleniumhq.selenium　　　　　　　　 
+            selenium-java　　　　　　　　 
+            2.53.0
+
+　　　　　　　　 
+       org.seleniumhq.selenium　　　　　　　　
+       htmlunit-driver　　　　　　　　 
+       2.20
+
+
+

data/全程软件测试（第3版）/第03章 准备：基础设施与TA框架/3.4 自动化测试框架/code_3.java

+java -jar selenium-server-standalone-x.xx.x.jar -role hub　
+    java -jar selenium-server-standalone-x.xx.x.jar -role node -port 5551　
+java -jar selenium-server-standalone-x.xx.x.jar -role node -port 5552　
+……
\ No newline at end of file

data/全程软件测试（第3版）/第03章 准备：基础设施与TA框架/3.4 自动化测试框架/code_4.java

+public class EditorTest extends
+                ActivityInstrumentationTestCase2 {
+  private Solo solo;
+  public EditorTest(){
+                super(EditorActivity.class);
+}
+public void setUp() throws Exception {
+      solo = new Solo(getInstrumentation(),getActivity());
+}
+public void testPreferenceIsSaved() throws Exception {
+              solo.sendKey(Solo.MENU);
+              solo.clickOnText("More");
+              solo.clickOnText("Preferences");
+              solo.clickOnText("Edit File Extensions")
+              solo.clickOnText(solo.searchText("rtf"));
+              solo.clickOnText("txt");
+              solo.clearEditText(2);
+              solo.enterText(2,"robotium");
+              solo.clickOnButton("Save");
+              solo.goBack();
+              solo.clickOnText("Edit File Extensions");
+              Assert.assertTrue(solo.searchText("application/robotium"));
+  }
+   @Override
+   public void tearDown() throws Exception {
+        solo.finishOpenedActivities();
+  }
\ No newline at end of file

data/全程软件测试（第3版）/第03章 准备：基础设施与TA框架/3.4 自动化测试框架/code_5.java

+Feature: Refund item
+
+  Scenario: Jeff returns a faulty microwave
+    Given Jeff has bought a microwave for $100
+    And he has a receipt
+    When he returns the microwave
+    Then Jeff should be refunded $100
\ No newline at end of file

main.py

+from src.ebook.extract_book_code import extract_code
+
+if __name__ == "__main__":
+    extract_code()

src/ebook/ebook_get_request.py

+import json
+import requests
+import logging
+
+
+logger = logging.getLogger(__name__)
+
+
+def get_chapter_content(params):
+    url = 'http://192.168.50.117:9003/v1/chapter/content'
+
+    headers = {
+        "Cookie":"UserToken=149ba8a7a8d341bbbe41f904c4c9b176;UserName=xiuxiuyayayy"
+    }
+
+    result = requests.get(url=url, params=params, headers=headers)
+
+    if result.status_code == 200:
+        ret = json.loads(result.text)
+        logger.info('request success')
+        content = ret['data']
+        return content
+    else:
+        logger.info('request failed！！！！！')
+        return {}
+
+
+def get_chapter_list(params):
+    url = 'http://192.168.50.117:9003/inner/v1/chapter/list'
+
+    headers = {
+        "Cookie":"UserToken=149ba8a7a8d341bbbe41f904c4c9b176;UserName=xiuxiuyayayy"
+    }
+
+    result = requests.get(url=url, params=params, headers=headers)
+
+    if result.status_code == 200:
+        ret = json.loads(result.text)
+        logger.info('request success')
+        content = ret['data']
+        return content
+    else:
+        logger.info('request failed！！！！！')
+        return {}
\ No newline at end of file

src/ebook/extract_book_code.py

+import json
+import os
+import re
+import html
+from bs4 import BeautifulSoup
+from .get_book_chapter_id_list import get_chapter_id_list
+from .ebook_get_request import get_chapter_content
+
+
+def extract_code():
+
+    book_mapping_path = "data/book_mapping.json"
+    with open(book_mapping_path, "r") as f:
+        book_mapping = json.load(f)
+    for book_idx, book_name in enumerate(book_mapping.keys()):
+        if book_name == 'Python编程无师自通':
+            continue
+        book_dir_name = '{}.{}'.format(book_idx + 1, book_name)
+        book_dir = os.path.join('data/books', book_dir_name)
+        if not os.path.exists(book_dir):
+            os.mkdir(book_dir)
+        print(book_dir_name)
+        book_id = book_mapping[book_name]
+        request_get_chapter_id_list_params = {"bookId": book_id, "is_main": 1}
+        chapter_id_list = get_chapter_id_list(
+            request_get_chapter_id_list_params)
+        print(chapter_id_list)
+        for chapter_id in chapter_id_list:
+            request_get_chapter_content_params = {
+                'bookId': book_id,
+                'chapterId': chapter_id
+            }
+            chapter_resp = get_chapter_content(
+                request_get_chapter_content_params)
+            chapter_name = chapter_resp['name']
+            chapter_content = chapter_resp['content']
+            try:
+                if book_name == "零基础学机器学习":
+                    chapter_num = re.findall(r'第(.*)课', chapter_name)[0]
+                    chapter_name_modify = re.sub(
+                        r'第(.*)课', r'第{}课'.format(chapter_num.zfill(2)),
+                        chapter_name)
+                else:
+                    chapter_num = re.findall(r'第(.*)章', chapter_name)[0]
+                    chapter_name_modify = re.sub(
+                        r'第(.*)章', r'第{}章'.format(chapter_num.zfill(2)),
+                        chapter_name)
+                chapter_name = chapter_name_modify
+            except:
+                # print('该章节没有章节序号： {}'.format(chapter_name))
+                pass
+            chapter_dir = os.path.join(book_dir, chapter_name)
+            if not os.path.exists(chapter_dir):
+                os.mkdir(chapter_dir)
+                # print('创建文件夹： {}'.format(chapter_dir))
+
+            chapter_content = html.unescape(chapter_content)
+
+            if book_name == "全程软件测试（第3版）":
+                section_list = re.findall(r'<h2.*>(.*?)</h2>', chapter_content)
+                section_content_list = re.split(r'<h2.*?>.*?</h2>',
+                                                chapter_content,
+                                                flags=re.S)
+                section_dir_list = []
+                for section in section_list:
+                    section = section.replace('　', ' ')
+                    if section.find(r'/') != -1:
+                        section = section.replace('/', '')
+                    section_dir = os.path.join(chapter_dir, section)
+                    print(section_dir)
+                    if not os.path.exists(section_dir):
+                        os.mkdir(section_dir)
+                    section_dir_list.append(section_dir)
+                for idx, section_content in enumerate(section_content_list):
+                    if idx == 0:
+                        save_dir = os.path.join(chapter_dir, 'text.html')
+                    else:
+                        save_dir = os.path.join(section_dir_list[idx - 1],
+                                                'text.html')
+                    code_list = re.findall(r'<code>(.*?)</code>',
+                                           section_content, re.S)
+
+                    res_code_list = []
+                    count = 0
+                    for i in code_list:
+                        if len(i.split('\n')) < 2:
+                            continue
+                        count += 1
+                        i = html.unescape(i)
+                        soup = BeautifulSoup(i)
+                        res_str = soup.get_text()
+
+                        if idx == 0:
+                            code_save_dir = os.path.join(
+                                chapter_dir, 'code_0.java')
+                        else:
+                            code_save_dir = os.path.join(
+                                section_dir_list[idx - 1],
+                                'code_{}.java'.format(count))
+
+                        print(res_str)
+                        with open(code_save_dir, 'w', encoding='utf-8') as f:
+                            f.write(res_str)
+
+                        # clean_text_list = []
+                        # for line in res_str.split('\n'):
+                        #     if line == '':
+                        #         continue
+                        #     if line[0].isdigit():
+                        #         line = re.findall(r'^[0-9]+ {0,2}(.*)',
+                        #                           line)[0]
+                        #         # print(line)
+                        #     else:
+                        #         if line.startswith('>>'):
+                        #             break
+                        #     clean_text_list.append(line)
+                        # clean_code = '\n'.join(clean_text_list)
+                        # print(clean_code)
\ No newline at end of file

src/ebook/get_book_chapter_id_list.py

+import json
+import re
+import html
+import nltk
+import html2text
+import os
+import pandas as pd
+from bs4 import BeautifulSoup
+from .ebook_get_request import get_chapter_list
+
+
+def get_chapter_id_list(param):
+    chapter_list = []
+    ret = get_chapter_list(param)
+    for item in ret:
+        chapterid = item['chapterid']
+        chapter_list.append(chapterid)
+    return chapter_list