解析BeautifulReport生成的html测试报告

用于处理BeautifulReport生成的测试报告，提取html文件中的字段信息
from bs4 import BeautifulSoup
from setting.config import *
import json
from string import digits
import requests


def get_html_info(html_name):
    '''
        获取测试报告中的内容
    param html_name:报告的名称
    return:json list
    '''
    htmlname = u'%s/%s' % (REPORT_PATH, html_name)
    # 获取文件对象
    html = BeautifulSoup(open(htmlname, encoding='utf-8'), features='html.parser')
    # 获取所有的文本
    text = html.get_text()
    # 字符串处理，把一些冗余的字符串处理掉
    text = text.replace('
', '')
    text = text.replace(' ', '')
    text = text.split("详细信息")[-1]
    text = text.split("查看详情")
    text_list_temp = []
    for i in text:
        if 'Traceback' not in i:
            text_list_temp.append(i)
        elif 'Traceback' in i:
            i = i.split('】')[-1]
            text_list_temp.append(i)
    # 将结果提取出来，组装成一个列表
    res_json_list = []
    for text in text_list_temp[0:-1]:
        suite_name = text.split('Test')[-1].split('test')[0]
        i = text.split('_')[-1].split("：")
        case_id = i[0][-3:]
        case_id = int(case_id)
        case_title = i[1].split('.')[0]
        # remove digits
        case_title = case_title.translate(str.maketrans('', '', digits))
        # 转换结果
        result = i[1].split('s')[-1]
        if result == '成功':
            result = 'pass'
        else:
            result = 'fail'
        # 结果组成字典, product_id, task_id
        res_dict = {
            # 'product_id': 42440,
            'testtask_name':'集成测试',
            'suite_name': suite_name,
            # 'task_id': 43641,
            'case_id': case_id,
            'test_type':'UI',
            'result': result,
            'reals': case_title,
            'area':'成都',
            'user_name': 'mikigo'
        }
        # dict —> json
        res_json = json.dumps(res_dict, ensure_ascii=False)
        res_json_list.append(res_json)
    return res_json_list