modified: resume_parse.py

tools/resume_parse.py

@@ -9,13 +9,10 @@ from pprint import pprint
 import logging
 logging.basicConfig(format='%(asctime)s: %(name)s: %(levelname)s: %(filename)s: %(funcName)s: %(message)s', level=logging.INFO)
 
-import jieba
 import pandas as pd
 from docx import Document
 from docx.shared import Inches
 
-from numpy import mean, median, bincount, argmax
-
 from pdfminer.high_level import extract_pages
 from pdfminer.layout import LTTextContainer, LTChar, LTLine, LAParams, LTTextBox, LTFigure, LTImage, LTText, LTAnno, LTTextLine, LTTextLineHorizontal
 from pdfminer.pdfdocument import PDFDocument
@@ -61,7 +58,7 @@ block_rev = {1:"基本信息", 2:"求职意向", 3:"教育经历", 4:"工作经
 
 # 基本信息(已完成)
 def get_base_info(lines):
-    pprint(lines)
+    logging.debug(lines)
     schema = {
         '姓名': None,
     }
@@ -69,8 +66,6 @@ def get_base_info(lines):
         line = line.replace(r'[ ]{5,}','\n')
         w = re.sub(r'[\W]+(\w[:：])[\W]{0,}\w', r'\1', line)
 
-        pprint(w)
-
         for i in w.split():
             if '：' in i:
                 try:
@@ -78,12 +73,6 @@ def get_base_info(lines):
                     schema[key] = val
                 except Exception as e:
                     logging.error(e)
-            if ':' in i:
-                try:
-                    key, val = i.split('：')
-                    schema[key] = val
-                except Exception as e:
-                    logging.error(e)
 
         if not schema.get('姓名'):
             schema['姓名'] = re.search(r'[姓名:：]{3,}(\w{2,4})', w).group(1) if re.search(r'[姓名:：]{3,}(\w{2,4})', w) else None
@@ -95,16 +84,14 @@ def get_base_info(lines):
             schema['性别'] = re.search(r'[男女]', w).group() if re.search(r'[男女]', w) else None
         if not schema.get('婚姻状况'):
             schema['婚姻状况'] = re.search(r'[已未]婚', w).group() if re.search(r'[已未]婚', w) else None
-        # if not schema.get('籍贯'):
-        #     schema['籍贯'] = re.search(r'[籍贯:：]{3,}(\w{2,5})', w).group(1) if re.search(r'[籍贯:：]{3,}(\w{2,})', w) else None
-        # if not schema.get('学历'):
-        #     schema['学历'] = re.search(r'[学历:：]{3,}(\w{2,4})', w).group(1) if re.search(r'[学历:：]{3,}(\w{2,4})', w) else None
         if not schema.get('电子邮箱'):
             schema['电子邮箱'] = re.search(r'([.\w]+@[.\w]+)', w).group() if re.search(r'([.\w]+@[.\w]+)', w) else None
         if not schema.get('政治面貌'):
             schema['政治面貌'] =  re.search(r'[预备中共党团员群众无派人士]{2,6}', w).group() if re.search(r'[预备中共党团员群众无派人士]{2,6}', w) else None
         if not schema.get('手机号码'):
             schema['手机号码'] = re.search(r'\W(1[\d]{10})\W', w).group(1) if re.search(r'\W(1[\d]{10})\W', w) else None
+        # if not schema.get('籍贯'):
+        #     schema['籍贯'] = re.search(r'[籍贯:：]{3,}(\w{2,5})', w).group(1) if re.search(r'[籍贯:：]{3,}(\w{2,})', w) else None
         # if not schema.get('出生年月'):
         #     schema['出生年月'] = re.search(r'\d{4}[./年\-]\d{1,2}[月]', w).group() if re.search(r'\d{4}[./年\-]\d{1,2}[月]', w) else None
         # if not schema.get('当前职位'):
@@ -116,7 +103,7 @@ def get_base_info(lines):
 
 # 求职意向(已完成)
 def get_job_intention(lines):
-    pprint(lines)
+    logging.debug(lines)
     schema = {}
     for line in lines:
         regex = re.compile(r'\W{0,3}[：:]\s+')
@@ -131,10 +118,10 @@ def get_job_intention(lines):
     return schema
 
 
-# 教育经历 (已完成)
+# 教育经历 (已停用)
 # ner + 分词 (判断学校，时间，学历)  专业需要单独处理。
 def get_edu_list_old(lines):
-    pprint(lines)
+    logging.debug(lines)
 
     job_list = []
     job_dict = {'edu_time_beg':'', 'edu_time_end':'', 'edu_name':'','edu_leval':'','edu_domain':'', 'edu_statue':0}
@@ -294,8 +281,6 @@ def get_edu_list_old(lines):
                     break
 
         job_dict['edu_domain'] = edu_domain
-        # print(job_dict)
-        # print(_list_data)
 
         if len(job_list) ==0:
             job_list.append(job_dict)
@@ -355,7 +340,7 @@ def get_edu_list_old(lines):
 
 # 教育经历改 (已完成)
 def get_edu_list(lines):
-    pprint(lines)
+    logging.debug(lines)
 
     edu_list = [{"Time":None, "startTime":None, "endTime":None, "edu_name":None, "edu_domain":None, "edu_level":None}]
     regex_time = re.compile(r'((\d{4})[年\W]{1,2}(\d{1,2})[月\W]?[\d]{0,2})[至到\W]+((\d{4})[年\W]{1,2}(\d{1,2})[月\W]?)?([今])?|(\d{4})[至\W]+([\d今]{4})')
@@ -380,29 +365,38 @@ def get_edu_list(lines):
                     edu_list.append({"Time":None, "startTime":None, "endTime":None, "edu_name":None, "edu_domain":None, "edu_level":None})
                     count += 1
                 edu_list[count]["startTime"] = '{:4d}-{:02d}'.format(int(edu_time.group(2)),int(edu_time.group(3)))
+                # 年月日
                 if edu_time.group(5) != None:
                     edu_list[count]["endTime"] = '{:4d}-{:02d}'.format(int(edu_time.group(5)),int(edu_time.group(6)))
                     edu_list[count]["Time"] = '{:4d}-{:02d}~{:4d}-{:02d}'.format(int(edu_time.group(2)),int(edu_time.group(3)),int(edu_time.group(5)),int(edu_time.group(6)))
+                # 只有年
                 elif edu_time.group(8) != None:
                     edu_list[count]["Time"] = '{:4d}~{:4d}'.format(int(edu_time.group(8)),int(edu_time.group(9)))
                     edu_list[count]["startTime"] = '{:4d}'.format(int(edu_time.group(8)))
                     edu_list[count]["endTime"] = '{:4d}'.format(int(edu_time.group(9)))
+                # 至今类
                 else:
                     edu_list[count]["endTime"] = edu_time.group(7)
                     edu_list[count]['Time'] = '{:4d}-{:02d}~{}'.format(int(edu_time.group(2)),int(edu_time.group(3)),edu_time.group(7))
                 flags = 1
+            # 只有毕业时间
             elif edu_end_time:
+                # 提交信息
                 if edu_list[count].get("endTime") and edu_list[count].get("edu_name"):
                     edu_list.append({"Time":None, "startTime":None, "endTime":None, "edu_name":None, "edu_domain":None, "edu_level":None})
                     count += 1
+                # 年月
                 if edu_end_time.group(2):
                     edu_list[count]["Time"] = '{:4d}-{:02d}~{:4d}-{:02d}'.format(int(edu_end_time.group(1)),int(edu_end_time.group(2)),int(edu_end_time.group(1))-3,int(edu_end_time.group(2)))
                     edu_list[count]["endTime"] = '{:4d}-{:02d}'.format(int(edu_end_time.group(1)),int(edu_end_time.group(2)))
+                # 只有年
                 elif edu_end_time.group(1):
                     edu_list[count]["Time"] = '{:4d}~{:4d}'.format(int(edu_end_time.group(1)),int(edu_end_time.group(1))-3)
                     edu_list[count]["endTime"] = '{:4d}'.format(int(edu_end_time.group(1)))
+            # 学历
             if (not edu_list[count].get("edu_level")) and edu_level:
                 edu_list[count]["edu_level"] = edu_level.group(0)
+            # WordTag 识别 学校/专业
             for word, tag in ner_tag(cell):
                 if (not edu_list[count].get("edu_name")) and (tag == "组织机构类_教育组织机构"):
                     edu_list[count]["edu_name"] = word.strip()
@@ -411,14 +405,17 @@ def get_edu_list(lines):
                     edu_list[count]["edu_domain"] = word.strip()
                 elif edu_list[count].get("edu_name") and edu_list[count].get("edu_domain"):
                     break
+            # LAC 识别 学校
             else:
                 for word, tag in ner(cell):
                     if (tag == "ORG"):
                         edu_list[count]["edu_name"] = word
                         flags = 1
                         break
+            # 未识别成功时填充专业
             if (not (edu_level or flags or edu_list[count].get("edu_domain"))) and edu_domain:
                 edu_list[count]["edu_domain"] = edu_domain.group(0)
+    # 剔除时间不存在、学校不存在的列
     if (not edu_list[-1].get("Time")) or (not edu_list[-1].get("edu_name")):
         edu_list.pop()
     return edu_list
@@ -429,7 +426,7 @@ def get_edu_list(lines):
 # 其中，时间是判断是否下一份工作情况的主要标识符之一。字符数量
 # 时间类 数量词
 def get_job_list(lines):
-    pprint(lines)
+    logging.debug(lines)
 
     job_list = []
     re_txt = '\d{4,4}\040{0,2}.\d+\040{0,2}.?\040{0,2}[\-–至－\—～]{1,2}\040{0,2}\d{4,4}\040{0,2}.\040{0,2}\d+.?|\d{4,4}.\d+.?\040{0,2}[\-–－—]{0,2}\040{0,2}至?今|\d{4,4}.\d+.?\040{0,2}[\-–－]{1,2}\040{0,2}现在|\d{4,4}年\d+月\-\d{4,4}年\d+月|\d{4,4}年\d+月\-\~|\d{4,4}年\d+月[\-\~－]至今|\d{4,4}-\d+\040{0,2}[－\~至]\040{0,2}\d{4,4}-\d+|\d{4,4}-\d+\~|\d{4,4}-\d+\[~－]至今|\d{4,4}-\d+\040{0,2}至今'
@@ -453,7 +450,7 @@ def get_job_list(lines):
         elif len(year_list) == 1 and '至今' in lines[i]:
             nums.append(i)
     nums.append(len(lines))
-    # pprint(nums)
+    # logging.debug(nums)
     logging.debug('get_job_list :{}'.format(nums))
     for i in range(1, len(nums[:])):
         job_dict = {'job_time':'', 'job_leval':'','job_company':'','job_content':''}
@@ -471,11 +468,11 @@ def get_job_list(lines):
                 job_time = ['-'.join(year_list)]
             elif len(year_list) == 1 and '至今' in lines[i]:
                 job_time = [year_list[0] + '-' + '至今']
-            pprint("342{}".format(job_time))
+
         if not job_time:
             regex = re.compile(r'((\d{4})[年\W]+(\d{1,2})[\W]?[\w]?)[至到\W]+((\d{4})[年\W]+(\d{1,2})[\W]?[\w]?)?([今])?')
             job_time = [re.search(regex, data_list[0]).group(0)]
-            pprint("346{}".format(job_time))
+
         job_dict['job_time'] = job_time[0]
         _nums = re.findall('\d+', job_dict['job_time'])
         #print(_nums)
@@ -612,7 +609,7 @@ def get_job_list(lines):
 # 项目经历 (已完成)
 # 项目名称未知
 def get_pro_list(lines):
-    pprint(lines)
+    logging.debug(lines)
 
     pro_list = [{"Time":None,"startTime":None,"endTime":None,"pro_name":None,"job_leval":None,"job_company":None,"content":None,},]
     regex = re.compile(r'((\d{4})[年\W]+(\d{1,2})[\W]?[\w]?)[至到\W]+((\d{4})[年\W]+(\d{1,2})[\W]?[\w]?)?([今])?')
@@ -624,13 +621,6 @@ def get_pro_list(lines):
         regex_content = re_con.search(line)
         regex_name = re_na.search(line)
         if regex_time:
-
-            # data_list = line.split()
-            # # for i in regex_time.groups():
-            # #     data_list.remove(i)
-            # console.print(regex_time.groups(), style='red', justify='left')
-            # console.print(data_list, style='red', justify='left')
-
             if pro_list[count].get("Time"):
                 pro_list.append({"Time":None,"startTime":None,"endTime":None,"pro_name":None,"job_leval":None,"job_company":None,"content":None,})
                 count += 1
@@ -661,7 +651,7 @@ def get_pro_list(lines):
 # 培训经历 (已完成)
 # ner + 分词 （机构名） 培训项目  时间
 def get_cultivate_list(lines):
-    pprint(lines)
+    logging.debug(lines)
 
     job_list = []
     re_txt = '\d{4,4}.\d{1,2}.?\040{0,2}[\-–至－\—～]\040{0,2}\d{4,4}.\d{1,2}[月]?|\d+\.\d+\-至今|\d+年\d+月\-\d+年\d+月|\d+年\d+月\-\~|\d+年\d+月[\-\~]至今|\d+-\d+\040{0,2}[\~至]\040{0,2}\d+-\d+|\d+-\d+\~|\d+-\d+\~至今|\d+-\d+\040{0,2}至今|^\d{4,4}.\d{1,2}|\d{4,4}.'
@@ -783,15 +773,13 @@ def get_cultivate_list(lines):
         else:
             job_dict['cultivate_content'] = re.sub('培培训训内内容容|培培训训内内容容：：|培培训训内内容容::', '培训内容：', ''.join(data_list[0:]))
         #print(job_dict)
-    
-        
     '''
     return job_list
 
 
 # 语言能力
 def get_lag_list(lines):
-    pprint(lines)
+    logging.debug(lines)
 
     job_list = []
     re_lan = re.compile(r'(\w+[语话])')
@@ -810,7 +798,6 @@ def get_lag_list(lines):
 # 家庭情况
 def get_fam_list(lines):
     job_list = []
-    #re_txt = '\d+年\d+月\-\d+年\d+月|\d+年\d+月\-\~|\d+年\d+月[\-\~]至今|\d+-\d+\~\d+-\d+|\d+-\d+\~|\d+-\d+\~至今'
     fam_dict = {}
     for l in lines:
         if not l.strip():
@@ -834,7 +821,7 @@ def get_fam_list(lines):
 
 # 证书情况  时间+证书名称 （已完成）
 def get_cet_list(lines):
-    pprint(lines)
+    logging.debug(lines)
 
     job_list = []
     re_txt = '\d+年\d+月|\d+-\d+|\d+\.\d+'
@@ -863,14 +850,13 @@ def get_cet_list(lines):
                 continue
             cet_dict['prize_name'] = l.strip()
             break
-        #print(cet_dict)
         job_list.append(cet_dict)
     return job_list
 
 
 # 获奖情况  时间+获奖名称 （已完成）
 def get_prize_list(lines):
-    pprint(lines)
+    logging.debug(lines)
 
     job_list = []
     re_txt = '\d+年\d+月|\d+-\d+|\d{4,4}.\d{1,2}'
@@ -957,11 +943,13 @@ def parse_txt(path):
                 page[chun] = []
             elif line:
                 page[chun].append(line)
+
+    result_data = []
     for key in page.keys():
         for index, func in zip([1, 2, 3, 4, 5, 9, 10, 11, 12], [get_base_info, get_job_intention, get_edu_list, get_job_list, get_pro_list, get_lag_list, get_cet_list, get_prize_list, get_cultivate_list]):
             if key == index:
-                console.print(block_rev[index], style="yellow", justify="left")
-                console.print(func(page[index]), style="green", justify="left")
+                result_data.append({block_rev[index]:func(page[index])})
+    console.print(result_data)
 
 
 # 纯文本 word 解析
@@ -983,15 +971,12 @@ def read_from_word(doc):
         elif line:
             page[chun].append(line)
 
+    result_data = []
     for key in page.keys():
         for index, func in zip([1, 2, 3, 4, 5, 10, 11, 12], [get_base_info, get_job_intention, get_edu_list, get_job_list, get_pro_list, get_cet_list, get_prize_list, get_cultivate_list]):
             if key == index:
-                console.print(block_rev[index])
-                try:
-                    console.print(func(page[index]), justify="left")
-                except Exception as e:
-                    logging.error(e)
-    return ''
+                result_data.append({block_rev[index]:func(page[index])})
+    console.print(result_data)
 
 
 # 提取 word 表格(已完成)
@@ -1000,9 +985,9 @@ def check_word(path):
     tables = doc.tables
 
     if not tables:
-        logging.info("this is raw text")
+        logging.debug("this is raw text")
         read_from_word(doc)
-    logging.info("this is a Table")
+    logging.debug("this is a Table")
 
     prk = {"姓名":1, "性别":1, "出生年月":1, "民族":1, "籍贯":1, "户籍地":1, "政治面貌":1, "参加工作时间":1, "健康状况":1, "专业技术资格":1, "外语水平":9, "熟悉专业有何专长":8, "学历学位":1, "工作单位":1, "现任职务":1, "任职时间":1, "提职时间":1, "联系电话":1, "邮箱地址":1, "称谓":13, "工作单位及职务":1, "毕业时间、院校及专业":3,}
     block = {
@@ -1021,10 +1006,10 @@ def check_word(path):
         "家庭成员":13, "家家庭庭成成员员":13, "家庭成员家庭成员":13, "主要家庭成员及社会关系":13,
         "社会活动":"other", "实践经验":"other", "社会活动及社会实践":"other", "近三年年度考核结果":"other", "其他意愿":"other",
     }
-    regex = re.compile(r'(\(\w{2,8}\))?(（\w{2,8}）)?')
 
     chun = 1
     page = {1: []}
+    regex = re.compile(r'(\(\w{2,8}\))?(（\w{2,8}）)?')
     for table in tables:
         lo = {} # 存储每一行去重后的数据
         for row in range(0, len(table.rows)):
@@ -1062,12 +1047,12 @@ def check_word(path):
                 line = line.replace(k+"\n", k+"：")
             page[chun].extend(line.split())
 
+    result_data = []
     for key in page.keys():
         for index, func in zip([1, 2, 3, 4, 5, 10, 11, 12], [get_base_info, get_job_intention, get_edu_list, get_job_list, get_pro_list, get_cet_list, get_prize_list, get_cultivate_list]):
             if key == index:
-                console.print(block_rev[index])
-                console.print(func(page[index]), justify="left")
-    return ''
+                result_data.append({block_rev[index]:func(page[index])})
+    console.print(result_data)
 
 
 # pdf 解析句子(已完成)
@@ -1086,7 +1071,6 @@ def parse_line_layout(layout):
                     texts.append([char.bbox[0], char.bbox[3], char.get_text().strip()])
     # 按行排序
     texts.sort(key=lambda x:-x[1])
-    # print(texts)
     global block, block_rev
 
     chun = 1
@@ -1134,15 +1118,12 @@ def read_from_pdf(path):
                     result[key] = r[key]
         block_rev = {1:"基本信息",2:"求职意向",3:"教育经历",4:"工作经历",5:"项目经历",6:"专业技能",7:"自我评价",8:"兴趣爱好",9:"语言能力",10:"证书",11:"获奖情况",12:"培训经历",13:"家庭成员","other":"其他"}
 
+        result_data = []
         for key in result.keys():
             for index, func in zip([1, 2, 3, 4, 5, 9, 10, 11, 12], [get_base_info, get_job_intention, get_edu_list, get_job_list, get_pro_list, get_lag_list, get_cet_list, get_prize_list, get_cultivate_list]):
                 if key == index:
-                    console.print(block_rev[index])
-                    console.print(func(result[index]), justify="left")
-                    # try:
-                    #     console.print(func(result[index]), justify="left")
-                    # except Exception as e:
-                    #     logging.error(e)
+                    result_data.append({block_rev[index]: func(result[index])})
+        console.print(result_data)
 
 
 # pdf 表格解析 ()
@@ -1162,7 +1143,7 @@ def parse_table_from_pdf(path):
                             key = None
     for key in block.keys():
         if result.get(key):
-            pprint({key: result[key]})
+            logging.debug({key: result[key]})
     console.print(result)
     # for key in result.keys():
     #     for index, func in zip([1, 2, 3, 4, 5, 10, 11, 12], [get_base_info, get_job_intention, get_edu_list, get_job_list, get_pro_list, get_cet_list, get_prize_list, get_cultivate_list]):