公司要求内部每日整理jira bug发邮件，手动执行了一段时间，想着用自动化的方式实现，故用了3天的时间做出了此脚本。
第一版基础版
# -*- coding:utf-8 -*- import requests import re from bs4 import BeautifulSoup as bs import time import os jql = "project = SDP and parent = SDP-13330 AND issuetype in (standardIssueTypes(), subTaskIssueTypes(), BUG) AND status in (新建, 解决中, 重新打开) AND priority in (P0, P1, P2) AND reporter in (membersOf(SDP_Tester)) ORDER BY priority DESC" username = "robin.li" password = "a12345678" tempfilepath = r"f:\bug_list.csv" outbuglist = r"f:\bug_out" + time.strftime("%Y%m%d", time.localtime()) + ".csv" parentid = "SDP-13330" bugs_list = [] def findall_data(data,LB="",RB=""): ''' 关联函数左右边界提取数取 ''' rule=LB + r"(.+?)" + RB datalist=re.findall(rule,data) return datalist def get_bugs_list(): '''根据规则提取bug列表''' if os.path.exists(outbuglist): # 如果文件存在 os.remove(outbuglist) with open(r"f:\bug_list.csv", 'r') as f: content = str(f.readlines())[1:-1] bug = [] soup = bs(content, features='html.parser') for tr in soup.select('tr'): for td in tr.select('td'): bug.append(str(td.text).strip(r'')) bugs_list.append(bug) bug = [] for bug in bugs_list: clear_list = str(bug[1:-2]).replace("\\n", "").replace("\'", "").replace(" ", "").replace("\,", "").replace("\\xa0", "").replace(parentid, "").replace("[", "").replace("]", "") print(clear_list) try: with open(outbuglist, 'a') as f: f.write(clear_list + "\n") except PermissionError: print("\033[31m请关闭已经打开的bug列表") return 0 else: print("\n \033[31mbug列表输出地址：" + outbuglist + "\n" + "-"*50 + "-----bug内容如上：--------\n") def login_bugwriter(username, password, jql, tempfilepath): """ login_bugwriter(username='str',password='str', jql='str') 登录jira提取bug列表写入文件 username:登录Jira的帐号 password:密码 jql:jira过滤的语法 tempfilepath:过滤的bug文件临时存储目录文件 """ '''''' data = {'os_username': username, 'os_password': password, 'login': '登录'} res = requests.get("https://jira.clouddeep.cn/secure/Dashboard.jspa") if res.status_code == 200: print("可以访问Jira，开始提取数据") jsession = requests.Session() cookie_jar = jsession.post("https://jira.clouddeep.cn/login.jsp",data=data).cookies login_cookie = requests.utils.dict_from_cookiejar(cookie_jar) print("登录成功，整理列表") headers={ "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36", "Sec-Fetch-Dest": "document", "Sec-Fetch-Mode": "navigate", "Sec-Fetch-Site": "none", "Sec-Fetch-User": "?1", "Upgrade-Insecure-Requests": "1", } r=requests.get("https://jira.clouddeep.cn/browse/SDP-13330",headers=headers, cookies=login_cookie) #print(r.text) jql_url="https://jira.clouddeep.cn/issues/SDP-13330/?jql=" + jql print("请确认过滤条件：==>" + jql_url + "\n" + "-"*30) bug_list = requests.get(jql_url ,headers=headers, cookies=login_cookie) with open(tempfilepath,'w') as f: f.write(bug_list.text) else: print("jira无法访问，请检查网络。") if __name__ == '__main__': login_bugwriter(username, password, jql, tempfilepath) get_bugs_list()
第二版基础版添加日期相差功能
# -*- coding:utf-8 -*- import requests import re from bs4 import BeautifulSoup as bs import time import os from datetime import datetime jql = "project = SDP and parent = SDP-13330 AND issuetype in (standardIssueTypes(), subTaskIssueTypes(), BUG) AND status in (新建, 解决中, 重新打开) AND priority in (P0, P1, P2) AND reporter in (membersOf(SDP_Tester)) ORDER BY priority DESC" username = "a.li@rc.cn" password = "Rc123456" tempfilepath = r"f:\bug_list.csv" outbuglist = r"f:\bug_out" + time.strftime("%Y%m%d", time.localtime()) + ".csv" parentid = "SDP-13330" bugs_list = [] def trans_month(date): ch_date_dict = {'一': '01', '二': '02', '三': '03', '四': '04', '五': '05', '六': '06', '七': '07', '八': '08', '九': '09', '十': '10', '十一': '11', '十二': '12', } old_date = date.split('/') ch_date = str(old_date[1])[0] if ch_date in ch_date_dict: old_date[1]=ch_date_dict[ch_date] new_date = "/".join(str(i) for i in old_date) return new_date else: print('日期格式错误') def diff_date(d1, d2): d1 = datetime.strptime(d1,'%d/%m/%y').date() return (d2 - d1).days def findall_data(data,LB="",RB=""): ''' 关联函数左右边界提取数取 ''' rule=LB + r"(.+?)" + RB datalist=re.findall(rule,data) return datalist def get_bugs_list(): '''根据规则提取bug列表''' if os.path.exists(outbuglist): # 如果文件存在 os.remove(outbuglist) with open(r"f:\bug_list.csv", 'r') as f: content = str(f.readlines())[1:-1] bug = [] soup = bs(content, features='html.parser') for tr in soup.select('tr'): for td in tr.select('td'): if td.text != " \\n": print('2==',len(bug)) bug.append(str(td.text).strip("")) if "<img" in str(td): #提取日期 get_date = tr.time.text # 09:30:45' d1 = trans_month(get_date) d2 = datetime.now().date() diff_days = diff_date(d1, d2) s = str(td.img['alt']) print('1==',len(bug)) bug.insert(len(bug),str(diff_days))
bug.append(s)
#print('1',bug) #print('2',bug) bugs_list.append(bug) #bugs_list = [i for i in bugs_list if i != ''] #print('3',bugs_list) bug = [] for bug in bugs_list: #ps = bug # print(len(bug)) # if len(bug) != 0: clear_list = str(bug[:-2]).replace("\\n", "").replace("\'", "").replace(" ", "").replace("\,", "").replace("\\xa0", "").replace(parentid, "").replace("[", "").replace("]", "") #print(clear_list) #clear_list = clear_list.split(",") #clear_list = [i for i in clear_list if i !=''] print(clear_list) try: with open(outbuglist, 'a') as f: f.write(str(clear_list) + "\n") except PermissionError: print("\033[31m请关闭已经打开的bug列表") return 0 else: print("\n \033[31mbug列表输出地址：" + outbuglist + "\n" + "-"*50 + "-----bug内容如上：--------\n") def login_bugwriter(username, password, jql, tempfilepath): """ login_bugwriter(username='str',password='str', jql='str') 登录jira提取bug列表写入文件 username:登录Jira的帐号 password:密码 jql:jira过滤的语法 tempfilepath:过滤的bug文件临时存储目录文件 """ '''''' data = {'os_username': username, 'os_password': password, 'login': '登录'} res = requests.get("https://jira.clouddeep.cn/secure/Dashboard.jspa") if res.status_code == 200: print("可以访问Jira，开始提取数据") jsession = requests.Session() cookie_jar = jsession.post("https://jira.clouddeep.cn/login.jsp",data=data).cookies login_cookie = requests.utils.dict_from_cookiejar(cookie_jar) print("登录成功，整理列表") headers={ "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36", "Sec-Fetch-Dest": "document", "Sec-Fetch-Mode": "navigate", "Sec-Fetch-Site": "none", "Sec-Fetch-User": "?1", "Upgrade-Insecure-Requests": "1", } r=requests.get("https://jira.clouddeep.cn/browse/SDP-13330",headers=headers, cookies=login_cookie) #print(r.text) jql_url="https://jira.clouddeep.cn/issues/SDP-13330/?jql=" + jql print("请确认过滤条件：==>" + jql_url + "\n" + "-"*30) bug_list = requests.get(jql_url ,headers=headers, cookies=login_cookie) with open(tempfilepath,'w') as f: f.write(bug_list.text) else: print("jira无法访问，请检查网络。") if __name__ == '__main__': #login_bugwriter(username, password, jql, tempfilepath) get_bugs_list()
第三版优化了提取器，实现一键提取bug
实现的代码
# -*- coding:utf-8 -*- import requests import re from bs4 import BeautifulSoup as bs import time import os from datetime import datetime parentid = "SDP-15642" #bug汇总 jira号 #查询条件 jql = "project = SDP and parent = " + parentid +" AND issuetype in (standardIssueTypes(), subTaskIssueTypes(), BUG) AND status in (新建, 解决中, 重新打开,解决中) AND priority in (P0, P1, P2) AND reporter in (membersOf(SDP_Tester)) ORDER BY priority DESC" tr_title = "JIRA链接,详细描述,BUG等级,经办人,报告人,JIRA状态,JIRA创建时间,bug持续时间"#["JIRA链接","详细描述","BUG等级","经办人","报告人","JIRA状态","JIRA创建时间","bug持续时间"] username = "aa.li@ss.cn" password = "ss2018()" tempfilepath = r"./bug_list.csv" outbuglist = r"./bug_out" + time.strftime("%Y%m%d", time.localtime()) + ".csv" # orderbuglist = r"./order_bug_out" + time.strftime("%Y%m%d", time.localtime()) + ".csv" bugs_list = [] def trans_month(date): ch_date_dict = {'一': '01', '二': '02', '三': '03', '四': '04', '五': '05', '六': '06', '七': '07', '八': '08', '九': '09', '十': '10', '十一': '11', '十二': '12', } old_date = date.split('/') ch_date = str(old_date[1])[0] if ch_date in ch_date_dict: old_date[1]=ch_date_dict[ch_date] new_date = "/".join(str(i) for i in old_date) return new_date else: print('日期格式错误') def diff_date(d1, d2): d1 = datetime.strptime(d1,'%d/%m/%y').date() return (d2 - d1).days def findall_data(data,LB="",RB=""): ''' 关联函数左右边界提取数取 ''' rule=LB + r"(.+?)" + RB datalist=re.findall(rule,data) return datalist def get_bugs_list(): '''根据规则提取bug列表''' # if os.path.exists(outbuglist): # 如果文件存在 # os.remove(outbuglist) with open(r"f:\bug_list.csv", 'r') as f: content = str(f.readlines())[1:-1] bug = [] soup = bs(content, features='html.parser') for tr in soup.select('tr'): for td in tr.select('td'): str1 = re.sub(r"[\\n'\s]","",str(td.text)) str2 = re.sub("[\s ,\r\n]{1,99}", ",", str1) if str2 != "": bug.append(str(str2).strip("")) if "<img" in str(td): #提取日期 get_date = tr.time.text # 09:30:45' d1 = trans_month(get_date) d2 = datetime.now().date() diff_days = diff_date(d1, d2) s = str(td.img['alt']) bug.insert(len(bug),str(diff_days)) bug.append(s) bugs_list.append(bug) bug = [] else: print("\n \033[31mbug列表输出地址：" + "\n" + "-"*50 + "-----bug内容如上：--------\n") return bugs_list def login_bugwriter(username, password, jql, tempfilepath): """ login_bugwriter(username='str',password='str', jql='str') 登录jira提取bug列表写入文件 username:登录Jira的帐号 password:密码 jql:jira过滤的语法 tempfilepath:过滤的bug文件临时存储目录文件 """ '''''' data = {'os_username': username, 'os_password': password, 'login': '登录'} res = requests.get("https://jira.clouddeep.cn/secure/Dashboard.jspa") if res.status_code == 200: print("可以访问Jira，开始提取数据") jsession = requests.Session() cookie_jar = jsession.post("https://jira.clouddeep.cn/login.jsp",data=data).cookies login_cookie = requests.utils.dict_from_cookiejar(cookie_jar) print("登录成功，整理列表") headers={ "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36", "Sec-Fetch-Dest": "document", "Sec-Fetch-Mode": "navigate", "Sec-Fetch-Site": "none", "Sec-Fetch-User": "?1", "Upgrade-Insecure-Requests": "1", } r=requests.get("https://jira.clouddeep.cn/browse/" + parentid,headers=headers, cookies=login_cookie) jql_url="https://jira.clouddeep.cn/issues/" + parentid + "/?jql=" + jql print("请确认过滤条件：==>" + jql_url + "\n" + "-"*30) bug_list = requests.get(jql_url ,headers=headers, cookies=login_cookie) with open(tempfilepath,'w') as f: f.write(bug_list.text) else: print("jira无法访问，请检查网络。") def order_buglist(buglist): with open(outbuglist,'w') as f: f.write(tr_title + '\n') print(tr_title) for l in buglist: if len(l) <= 1: print("列表长度小于1") else: s = l[3:4] + str(l[4:5]).split(",")[2:3] +l[2:3] + l[9:11] + l[5:6] + l[8:9] + l[1:2] s2 = re.sub(r"'","",str(s)[3:-1]) s3 = re.sub(r"[, ]{1,8}",",",s2) f.write("https://jira.clouddeep.cn/browse/" + str(s3) + '\n') print('out>>',s3) print("bug列表输出地址：\n",outbuglist) if os.path.exists(tempfilepath): os.remove(tempfilepath) else: print("no such file: %s" %tempfilepath) if __name__ == '__main__': login_bugwriter(username, password, jql, tempfilepath) bug = get_bugs_list() order_buglist(bug)
实现一键提取：
编写2个bat文件：
init_env.bat #初始化环境，安装所需的库
pip install requests
pip install bs4
get_jira_bugs.bat #调用主程序实现bug列表生成一个csv文件。
@ECHO OFF
python ./jiraCollection.py echo run success! pause
