extract name from pinyin list

src/person_name/convert_name_to_pinyin.py

@@ -0,0 +1,30 @@
+from pypinyin import pinyin, lazy_pinyin, Style
+
+
+def read_name_from_files_by_line():
+    # Using readlines()
+    file1 = open('/Users/lpan/Downloads/Chinese_Names_Corpus.txt', 'r')
+    file2 = open('pinyin_list.txt', 'w')
+    lines = file1.readlines()
+    count = 0
+    # Strips the newline character
+    for line in lines:
+        count += 1
+        print("Line{}: {}".format(count, line.strip()))
+        name_to_save = convert_name_to_pinyin(line.strip())
+        file2.writelines(name_to_save + "\n")
+        print(name_to_save)
+    file1.close()
+    file2.close()
+
+
+def convert_name_to_pinyin(name: str):
+    name_in_pinyin_list = lazy_pinyin(name)
+    true_list = []
+    for item in name_in_pinyin_list:
+        if item != '\ufeff':
+            true_list.append(item)
+    return true_list[0] + " " + "".join(true_list[1:len(true_list)])
+
+
+read_name_from_files_by_line()

src/person_name/extract_name_with_pinyinlist.py

@@ -0,0 +1,110 @@
+import itertools
+
+import xlsxwriter
+from pyhanlp import *
+from Pinyin2Hanzi import DefaultHmmParams
+from Pinyin2Hanzi import viterbi
+from itertools import combinations
+
+from src.db.mongo_manager import MongoDbManager
+from src.pojo.contact_pojo import ContactPojo
+from src.utils.excel_reader import get_random_phone_numbers, generate_email_from_name
+from src.utils.generate_random_passport_id import get_random_passport_id_number
+
+
+def get_ordered_combins(stuff):
+    list_to_return = []
+    for i, j in itertools.combinations(range(len(stuff) + 1), 2):
+        print(stuff[i:j])
+        list_to_return.append(stuff[i:j])
+    return list_to_return
+
+
+def get_better_list(list):
+    return list
+    # for name in list:
+    #     if len(name) == 2:
+    #         list.remove(name)
+    #         return list
+
+
+# 关键词提取
+
+def read_pinyin_list_from_file() -> list:
+    file2 = open('clean_list.txt', 'r')
+    lines = file2.readlines()
+    name_list = []
+    count = 0
+    for line in lines:
+        count += 1
+        print("Line{}: {}".format(count, line.strip()))
+        name_list.append(line.strip())
+    return name_list
+
+
+def generate_name_from_email(mail_address, pinyin_name_list):
+    # key_words = HanLP.extractKeyword(mail_address, 2)
+    # print(key_words)
+    # setence = "".join(key_words)
+    all_combins = get_ordered_combins(mail_address)
+    for i in all_combins:
+        word_to_test = "".join(i)
+        if len(word_to_test) >= 3:
+            # print("word to test is " + word_to_test)
+            for name in pinyin_name_list:
+                last_name = name.split(" ")[0]
+                first_name = name.split(" ")[-1]
+                if word_to_test in last_name:
+                    return last_name, first_name
+                elif word_to_test in first_name:
+                    return last_name, first_name
+
+    # 选择不重复的
+    # if len(pinyin_name_list) > 3:
+    #     return get_better_list(pinyin_name_list)
+    # else:
+    return None
+
+
+def write_new_contacts_to_excel(valid_contacts: list):
+    row = 0
+    col = 0
+    # Create a workbook and add a worksheet.
+    workbook = xlsxwriter.Workbook('real_name_contacts_{}.xlsx'.format(len(valid_contacts)))
+    header_data = ['name', 'phone', 'passport', 'email', 'note']
+    worksheet = workbook.add_worksheet()
+    header_format = workbook.add_format({'bold': True})
+
+    for col_num, data in enumerate(header_data):
+        worksheet.write(row, col_num, data, header_format)
+    row = row + 1
+    for info in valid_contacts:
+        info.phone = get_random_phone_numbers()
+        info.passport = get_random_passport_id_number()
+        # Iterate over the data and write it out row by row.
+        worksheet.write(row, col, "{} {}".format(info.last_name, info.first_name))
+        worksheet.write(row, col + 1, info.phone)
+        worksheet.write(row, col + 2, info.passport)
+        worksheet.write(row, col + 3, info.mail)
+        worksheet.write(row, col + 4, info.note)
+        row += 1
+    workbook.close()
+
+
+if __name__ == '__main__':
+    db_manager = MongoDbManager()
+    mail_list = db_manager.get_destination_emails()[1001:1200]
+    # mail_list = db_manager.get_destination_emails()[50:200]
+    generate_contacts = []
+    pinyin_name_list = read_pinyin_list_from_file()
+
+    for mail in mail_list:
+        contact = ContactPojo(mail=mail.mail, phone_number="", passport_number="", last_name="", first_name="")
+        spliteed = mail.mail.split("@")
+        possible_name_list = generate_name_from_email(spliteed[0], pinyin_name_list)
+        if possible_name_list is not None:
+            contact.last_name = possible_name_list[0]
+            contact.first_name = possible_name_list[1]
+        if len(contact.last_name) > 0 and len(contact.first_name) > 0:
+            generate_contacts.append(contact)
+    write_new_contacts_to_excel(generate_contacts)