修改导出docx的方式

This commit is contained in:
shuaikangzhou 2024-01-18 23:06:37 +08:00
parent 62154823cf
commit 4fa56b888a
4 changed files with 98 additions and 21 deletions

View File

@ -25,6 +25,7 @@ encoded_chars = b'\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0b\x0c\x0e\x0f\x10\x11\x
# 创建一个字典,将要删除的字符映射为 None
char_mapping = {char: None for char in encoded_chars}
def filter_control_characters(input_string):
"""
过滤掉不可打印字符
@ -39,6 +40,84 @@ def filter_control_characters(input_string):
class DocxExporter(ExporterBase):
def merge_docx(self, n):
self.process_num += 1
conRemark = self.contact.remark
origin_docx_path = f"{os.path.abspath('.')}/data/聊天记录/{conRemark}"
filename = f"{origin_docx_path}/{conRemark}_{n}.docx"
# print(all_file_path)
doc = docx.Document(filename)
if self.merged_doc_index == [-1, -1]:
self.document.append(doc)
self.merged_doc_index = [n, n]
else:
if n == self.merged_doc_index[0] - 1:
self.document.insert(0, doc)
self.merged_doc_index[0] -= 1
elif n == self.merged_doc_index[1] + 1:
self.document.append(doc)
self.merged_doc_index[1] += 1
else:
self.docs.append([doc, n])
self.docs_set.add(n)
new_docx = []
new_set = set()
# print(self.docs)
while new_set!=self.docs_set:
self.docs.sort(key=lambda x: x[1])
for doc_, index in self.docs:
if index == self.merged_doc_index[0] - 1:
self.document.insert(0, doc_)
self.merged_doc_index[0] -= 1
elif index == self.merged_doc_index[1] + 1:
self.document.append(doc_)
self.merged_doc_index[1] += 1
else:
new_docx.append([doc_, index])
new_set.add(index)
self.docs = new_docx
self.docs_set = new_set
os.remove(filename)
if self.process_num == self.child_thread_num:
# self.document.append(self.document)
file = os.path.join(origin_docx_path, f'{conRemark}.docx')
try:
self.document.save(file)
except PermissionError:
file = file[:-5] + f'{time.time()}' + '.docx'
self.document.save(file)
self.okSignal.emit(1)
def export(self):
self.child_threads = []
messages = msg_db.get_messages(self.contact.wxid, time_range=self.time_range)
# 计算每个子列表的长度
num = 1
# num = len(messages) // 500 +1
sublist_length = len(messages) // num
# 使用列表切片将列表分成n个子列表
divided_list = [messages[i:i + sublist_length] for i in range(0, len(messages), sublist_length)]
self.child_thread_num = len(divided_list)
self.process_num = 0
doc = docx.Document()
doc.styles["Normal"].font.name = "Cambria"
doc.styles["Normal"]._element.rPr.rFonts.set(qn("w:eastAsia"), "宋体")
self.document = Composer(doc)
self.merged_doc_index = [-1, -1]
self.docs = []
self.docs_set = set()
# self.document.append(self.document)
for i in range(self.child_thread_num):
child_thread = DocxExporterChildThread(self.contact, type_=self.DOCX, message_types=self.message_types,
time_range=self.time_range, messages=divided_list[i], index=i)
self.child_threads.append(child_thread)
child_thread.okSignal.connect(self.merge_docx)
child_thread.progressSignal.connect(self.progressSignal)
child_thread.start()
class DocxExporterChildThread(ExporterBase):
def text(self, doc, message):
type_ = message[2]
str_content = message[7]
@ -313,7 +392,7 @@ class DocxExporter(ExporterBase):
def export(self):
print(f"【开始导出 DOCX {self.contact.remark}")
origin_docx_path = f"{os.path.abspath('.')}/data/聊天记录/{self.contact.remark}"
messages = msg_db.get_messages(self.contact.wxid, time_range=self.time_range)
messages = self.messages
Me().save_avatar(os.path.join(f"{origin_docx_path}/avatar/{Me().wxid}.png"))
if self.contact.is_chatroom:
for message in messages:
@ -329,6 +408,8 @@ class DocxExporter(ExporterBase):
self.contact.save_avatar(os.path.join(f"{origin_docx_path}/avatar/{self.contact.wxid}.png"))
self.rangeSignal.emit(len(messages))
index = 0
def newdoc():
nonlocal n, doc
doc = docx.Document()
@ -347,8 +428,8 @@ class DocxExporter(ExporterBase):
for index, message in enumerate(messages):
if index % 200 == 0 and index:
# doc = document.add_paragraph()
filename = os.path.join(origin_docx_path, f"{self.contact.remark}{n}.docx")
doc.save(filename)
# filename = os.path.join(origin_docx_path, f"{self.contact.remark}{n}.docx")
# doc.save(filename)
newdoc()
type_ = message[2]
@ -391,6 +472,7 @@ class DocxExporter(ExporterBase):
for index, dx in enumerate(docs[::-1]):
print(f"【合并 DOCX {self.contact.remark}{index + 1}/{len(docs)}")
doc.insert(0, dx)
filename = os.path.join(origin_docx_path, f"{self.contact.remark}_{self.index}.docx")
try:
# document.save(filename)
doc.save(filename)
@ -399,4 +481,4 @@ class DocxExporter(ExporterBase):
# document.save(filename)
doc.save(filename)
print(f"【完成导出 DOCX {self.contact.remark}")
self.okSignal.emit(1)
self.okSignal.emit(self.index)

View File

@ -127,10 +127,7 @@ class HtmlExporter(ExporterBase):
if file_path != "":
file_path = './file/' + file_info.get('file_name')
doc.write(
f'''{{ type:49, text: '{file_path}',is_send:{is_send},avatar_path:'{avatar}',timestamp:{timestamp}
,is_chatroom:{is_chatroom},displayname:'{display_name}',icon_path: '{icon_path}'
,sub_type:6,file_name: '{file_info.get('file_name')}',file_size: '{file_info.get('file_len')}'
,app_name: '{file_info.get('app_name')}'}},'''
f'''{{ type:49, text: '{file_path}',is_send:{is_send},avatar_path:'{avatar}',timestamp:{timestamp},is_chatroom:{is_chatroom},displayname:'{display_name}',icon_path: '{icon_path}',sub_type:6,file_name: '{file_info.get('file_name')}',file_size: '{file_info.get('file_len')}',app_name: '{file_info.get('app_name')}'}},'''
)
def refermsg(self, doc, message):
@ -234,9 +231,7 @@ class HtmlExporter(ExporterBase):
display_name = self.get_display_name(is_send, message)
music_path = escape_js_and_html(music_path)
doc.write(
f'''{{ type:49, text:'{music_path}',is_send:{is_send},avatar_path:'{avatar}',link_url:'{content.get('link_url')}',
timestamp:{timestamp},is_chatroom:{is_chatroom},displayname:'{display_name}',sub_type:3,title:'{content.get('title')}',
artist:'{content.get('artist')}', website_name:'{content.get('website_name')}'}},'''
f'''{{ type:49, text:'{music_path}',is_send:{is_send},avatar_path:'{avatar}',link_url:'{content.get('link_url')}',timestamp:{timestamp},is_chatroom:{is_chatroom},displayname:'{display_name}',sub_type:3,title:'{content.get('title')}',artist:'{content.get('artist')}', website_name:'{content.get('website_name')}'}},'''
)
def share_card(self, doc, message):
@ -266,11 +261,7 @@ class HtmlExporter(ExporterBase):
else:
app_logo = card_data.get('app_logo')
doc.write(
f'''{{ type:49,sub_type:5, text:'',is_send:{is_send},avatar_path:'{avatar}',url:'{card_data.get('url')}',
timestamp:{timestamp},is_chatroom:{is_chatroom},displayname:'{display_name}',title:'{card_data.get('title')}',
description:'{card_data.get('description')}',thumbnail:'{thumbnail}',app_logo:'{app_logo}',
app_name:'{card_data.get('app_name')}'
}},\n'''
f'''{{ type:49,sub_type:5, text:'',is_send:{is_send},avatar_path:'{avatar}',url:'{card_data.get('url')}',timestamp:{timestamp},is_chatroom:{is_chatroom},displayname:'{display_name}',title:'{card_data.get('title')}',description:'{card_data.get('description')}',thumbnail:'{thumbnail}',app_logo:'{app_logo}',app_name:'{card_data.get('app_name')}'}},\n'''
)
def export(self):

View File

@ -90,19 +90,23 @@ class ExporterBase(QThread):
CONTACT_CSV = 4
TXT = 5
def __init__(self, contact, type_=DOCX, message_types={},time_range=None, parent=None):
def __init__(self, contact, type_=DOCX, message_types={}, time_range=None, messages=None,index=0, parent=None):
super().__init__(parent)
self.message_types = message_types # 导出的消息类型
self.contact: Contact = contact # 联系人
self.output_type = type_ # 导出文件类型
self.total_num = 1 # 总的消息数量
self.num = 0 # 当前处理的消息数量
self.index = index #
self.last_timestamp = 0
self.time_range = time_range
self.messages = messages
origin_docx_path = f"{os.path.abspath('.')}/data/聊天记录/{self.contact.remark}"
makedirs(origin_docx_path)
def run(self):
self.export()
def export(self):
raise NotImplementedError("export method must be implemented in subclasses")
@ -166,4 +170,4 @@ class ExporterBase(QThread):
return
def share_card(self, doc, message):
return
return

View File

@ -3,7 +3,7 @@ import os
import traceback
from typing import List
from PyQt5.QtCore import pyqtSignal, QThread
from PyQt5.QtCore import pyqtSignal, QThread, QObject
from PyQt5.QtWidgets import QFileDialog
from app.DataBase.exporter_csv import CSVExporter
@ -20,7 +20,7 @@ from ..util.image import get_image
os.makedirs('./data/聊天记录', exist_ok=True)
class Output(QThread):
class Output(QObject):
"""
发送信息线程
"""
@ -222,7 +222,7 @@ class Output(QThread):
Child.okSignal.connect(self.okSignal if not is_batch else self.batch_finish_one)
Child.start()
def run(self):
def start(self):
if self.output_type == self.DOCX:
self.to_docx(self.contact, self.message_types)
elif self.output_type == self.CSV_ALL: