def notes_extraction(file_name):
document = Document(file_name)
block_list = iter_block_items(document)
result_list = []
table_cnt = 0
for index in range(2, len(block_list)):
table = block_list[index]
table_name = []
df = DataFrame()
if type(table) == type(Table('', CT_Tbl)):
table_fmt = read_table(table)
df = trim_table_to_df(table_fmt)
# if (block_list[index-1] == '（续）' or block_list[index-1] == '' )and type(block_list[index-2]) == type(Table('',CT_Tbl)):
if (block_list[index - 1] == '') and type(
block_list[index - 2]) == type(Table('', CT_Tbl)):
table_ext = read_table(block_list[index - 2])
df = trim_table_to_df(table_ext)
result_list += [(file_name, result_list[table_cnt - 1][1], df)]
elif type(block_list[index - 1]) == type('') and type(
block_list[index - 2]) == type(Table('', CT_Tbl)):
table_name = [block_list[index - 1]]
result_list += [(file_name, table_name, df)]
elif type(block_list[index - 1]) == type('') and type(
block_list[index - 2]) == type(''):
table_name = [block_list[index - 2], block_list[index - 1]]
result_list += [(file_name, table_name, df)]
table_cnt += 1
return result_list
def iter_block_items(document):
document_elm = document.element.body
for child in document_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, document)
elif isinstance(child, CT_Tbl):
yield Table(child, document)
def row_cells_fixture(self, _cells_, _column_count_):
table = Table(None, None)
_cells_.return_value = [0, 1, 2, 3, 4, 5, 6, 7, 8]
_column_count_.return_value = 3
row_idx = 1
expected_cells = [3, 4, 5]
return table, row_idx, expected_cells
def col_cells_fixture(self, _cells_, _column_count_):
table = Table(None, None)
_cells_.return_value = [0, 1, 2, 3, 4, 5, 6, 7, 8]
_column_count_.return_value = 3
column_idx = 1
expected_cells = [1, 4, 7]
return table, column_idx, expected_cells
def iter_block_items(self, parent):
'''See https://github.com/python-openxml/python-docx/issues/40
Yield each paragraph and table child within *parent*, in document order.
Each returned value is an instance of either Table or Paragraph. *parent*
would most commonly be a reference to a main Document object, but
also works for a _Cell object, which itself can contain paragraphs and tables.
Commentary:
Cascade uses this function to walk through the Paragraphs and Tables
of a document in order. It is (currently) the only way in the
python-docx API to determine the physical location of tables
within a document.
'''
if isinstance(parent, docx_Document):
parent_elm = parent.element.body
elif isinstance(parent, _Cell):
parent_elm = parent._tc
else:
raise ValueError("Something is not right")
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent)
elif isinstance(child, CT_Tbl):
yield Table(child, parent)
def read_item_block(parent):
if isinstance(parent, _Document):
parent_elm = parent.element.body
elif isinstance(parent, _Cell):
parent_elm = parent._tc
elif isinstance(parent, _Row):
parent_elm = parent._tr
else:
raise ValueError("something's not right")
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
count = 1
count_flase = 0
res = Paragraph(child, parent)
if res.text != '':
yield (res, count_flase)
else:
try:
# 试着去取内联元素
from xml.dom.minidom import parseString
DOMTree = parseString(child.xml)
data = DOMTree.documentElement
nodelist = data.getElementsByTagName('pic:blipFill')
print('*nodelist' * 9, nodelist)
if len(nodelist) < 1:
yield (res, count_flase)
else:
yield (res, count)
except Exception as e:
print('*' * 9, e)
yield (res, count_flase)
elif isinstance(child, CT_Tbl):
yield (Table(child, parent), )
def iter_block_items(parent):
"""
Generate a reference to each paragraph and table child within *parent*,
in document order. Each returned value is an instance of either Table or
Paragraph. *parent* would most commonly be a reference to a main
Document object, but also works for a _Cell object, which itself can
contain paragraphs and tables.
"""
if isinstance(parent, _Document):
parent_elm = parent.element.body
elif isinstance(parent, _Cell):
parent_elm = parent._tc
elif isinstance(parent, _Row):
parent_elm = parent._tr
else:
raise ValueError("something's not right")
# TODO make this work for floating tables
# as do not necessarily appear in the same order in the document as they do visually
# Floating tables can be fixed in word doc by right clicking in table, choosing table properties,
# selecting None for text wrapping and clicking on ok.
# Then moving the table to the correct place.
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent)
elif isinstance(child, CT_Tbl):
yield Table(child, parent)
def add_column_fixture(self):
snippets = snippet_seq('add-row-col')
tbl = parse_xml(snippets[0])
table = Table(tbl, None)
width = Inches(1.5)
expected_xml = snippets[2]
return table, width, expected_xml
def _iter_block_items(parent):
"""
Generate a reference to each paragraph and table child within *parent*,
in document order. Each returned value is an instance of either Table or
Paragraph. *parent* would most commonly be a reference to a main
Document object, but also works for a _Cell object, which itself can
contain paragraphs and tables.
Author @scanny: https://github.com/python-openxml/python-docx/issues/276#issuecomment-199502885
"""
from docx.table import _Cell
from docx.oxml import CT_P
from docx.oxml import CT_Tbl
if isinstance(parent, DocType):
parent_elm = parent.element.body
elif isinstance(parent, _Cell):
parent_elm = parent._tc
else:
raise ValueError("something's not right")
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent)
elif isinstance(child, CT_Tbl):
yield Table(child, parent)
def iter_block_rpd_items(self, parent):
if isinstance(parent, Document):
parent_elm = parent.element.body
elif isinstance(parent, _Cell):
parent_elm = parent._tc
else:
raise ValueError("something's not right")
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent).text
elif isinstance(child, CT_Tbl):
table = Table(child, parent)
my_table = "Таблица: "
for row in table.rows:
try:
for cell in row.cells:
my_table += cell.text
my_table += '~'
except:
print('out of range')
pass
my_table += '@'
text = my_table
yield text
def docx_to_text(document_path, event_handler):
global logger
from docx import Document
from docx.table import Table
from docx.text.paragraph import Paragraph
from docx.oxml.table import CT_Tbl
from docx.oxml.text.paragraph import CT_P
try:
doc = Document(document_path)
doc_body = doc.element.body
blocks = []
for child in doc_body.iterchildren():
if isinstance(child, CT_P):
blocks.append(Paragraph(child, doc_body).text)
elif isinstance(child, CT_Tbl):
blocks.append('\n'.join(
' | '.join(cell.text for cell in row.cells)
for row in Table(child, doc_body).rows))
#end for
text = '\n\n'.join(blocks).strip()
return text
except Exception:
logger.exception('Exception while parsing <{}>.'.format(
event_handler.key))
#end try
# Extract it from the XML
with ZipFile(document_path) as document_zipfile:
xml_content = document_zipfile.read('word/document.xml')
try:
from xml.etree.cElementTree import XML
except ImportError:
from xml.etree.ElementTree import XML
tree = XML(xml_content)
DOCX_NAMESPACE = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}'
DOCX_PARA = DOCX_NAMESPACE + 'p'
DOCX_TEXT = DOCX_NAMESPACE + 't'
paragraphs = []
for paragraph in tree.getiterator(DOCX_PARA):
texts = [
node.text for node in paragraph.getiterator(DOCX_TEXT) if node.text
]
if texts:
paragraphs.append(''.join(texts))
#end for
text = '\n\n'.join(paragraphs)
return text
def table_style_fixture(self):
style = 'foobar'
tbl = (
a_tbl().with_nsdecls().with_child(
a_tblPr().with_child(
a_tblStyle().with_val(style)))
).element
table = Table(tbl)
return table, style
def iterate_paragraphs_and_tables(docx_document):
if isinstance(docx_document, _Document):
docx_document_elm = docx_document.element.body
else:
raise ValueError('ошибка при итерации по блокам docx')
for child in docx_document_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, docx_document)
elif isinstance(child, CT_Tbl):
yield Table(child, docx_document)
def iter_block_docx(parent):
if isinstance(parent, _Document):
parent_elm = parent.element.body
else:
raise ValueError("Something went right")
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent)
elif isinstance(child, CT_Tbl):
yield Table(child, parent)
def table_nested_parsing(cell, current_row, current_col):
for block in cell._element:
if isinstance(block, CT_P):
#(Paragraph(block, cell).text)
return (Paragraph(block, cell).text)
if isinstance(block, CT_Tbl):
block = Table(block, cell)
for row in range(len(block.rows)):
for col in range(len(block.columns)):
cell_table = block.cell(row, col)
table_nested_parsing(cell_table, row, col)
def iter_block_items(parent):
if isinstance(parent, _Document):
parent_elm = parent.element.body
elif isinstance(parent, _Cell):
parent_elm = parent._tc
elif isinstance(parent, _Row):
parent_elm = parent._tr
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent)
elif isinstance(child, CT_Tbl):
yield Table(child, parent)
def iter_block_items(parent):
if isinstance(parent, _Document):
parent_elm = parent.element.body
elif isinstance(parent, _Cell):
parent_elm = parent._tc
else:
raise ValueError("something's not right")
for child in parent_elm.iterchildren():
if isinstance(child, CT_P): #判断两个参数是否为同一类型，返回布尔型
yield Paragraph(child, parent)
elif isinstance(child, CT_Tbl):
yield Table(child, parent)
def iter_cell_items(self, parent):
parent_elm = parent._tc
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent)
elif isinstance(child, CT_Tbl):
table = Table(child, parent)
for row in table.rows:
for cell in row.cells:
yield from self.iter_cell_items(cell)
def table_style_set_fixture(self):
# table ------------------------
tbl = a_tbl().with_nsdecls().with_child(a_tblPr()).element
table = Table(tbl)
# style_name -------------------
style_name = 'foobar'
# expected_xml -----------------
expected_xml = (
a_tbl().with_nsdecls().with_child(
a_tblPr().with_child(
a_tblStyle().with_val(style_name)))
).xml()
return table, style_name, expected_xml
def doc_parsing(doc):
listField = []
listTable = []
fieldName = ''
fileDesc = ''
for doc_part in doc.element.body:
if isinstance(doc_part, CT_P):
pg = Paragraph(doc_part, doc).text
if (pg.find('<table_name>') >= 0 and pg.find('</table_name>') > 0):
fieldName = pg[pg.find('<table_name>') +
12:pg.find('</table_name>')] + '.java'
fileDesc = pg[0:pg.find('<table_name>')]
if (isinstance(doc_part, CT_Tbl) and fieldName != ''):
tableinfo = TableInfo()
tableinfo.fileName = fieldName
tableinfo.fileDesc = fileDesc
tb1 = Table(doc_part, doc)
isMytable = doc_mytable(tb1)
if (isMytable == False):
continue
for row in range(len(tb1.rows)):
if (row == 0):
continue
w2 = WordModel()
w2.field = getCellText(
tb1, row,
dict.get("field") if dict.has_key("field") else '')
w2.fieldName = getCellText(
tb1, row,
dict.get("fieldName") if dict.has_key("fieldName") else '')
w2.fieldType = getCellText(
tb1, row,
dict.get("fieldType") if dict.has_key("fieldType") else '')
w2.comment = getCellText(
tb1, row,
dict.get("comment") if dict.has_key("comment") else '')
w2.must = getCellText(
tb1, row,
dict.get("must") if dict.has_key("must") else '')
# print w2.display()
w2.fieldType = dataConvert(w2.fieldType)
listField.append(w2)
# for col in range(len(tb1.columns)):
# cell_table = tb1.cell(row, col)
# table_nested_parsing(cell_table, row, col)
tableinfo.listField = listField
listTable.append(tableinfo)
fieldName = ''
listField = []
return listTable
def read_item(parent):
if isinstance(parent, _Document):
parent_elm = parent.element.body
elif isinstance(parent, _Cell):
parent_elm = parent._tc
elif isinstance(parent, _Row):
parent_elm = parent._tr
else:
raise ValueError("something's not right")
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent)
elif isinstance(child, CT_Tbl):
yield Table(child, parent)
def iter_block_items(parent):
if isinstance(parent, docx.document.Document):
parent_elm = parent.element.body
elif isinstance(parent, docx.table._Cell):
parent_elm = parent._tc
elif isinstance(parent, docx.table._Row):
parent_elm = parent._tr
else:
raise ValueError("something's not right")
for child in parent_elm.iterchildren():
if isinstance(child, docx.oxml.text.paragraph.CT_P):
yield docx.text.paragraph.Paragraph(child, parent)
elif isinstance(child, docx.oxml.table.CT_Tbl):
yield Table(child, parent)
def paragraphs_tables(docx):
"""
merge tables and paragraphs together in docx
need it to keep order of text and tables of docx documents
"""
p_t_list = []
for content in docx._body._body.getchildren():
if content.tag == '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}p':
p_t_list.append(Paragraph(content, docx._body))
elif content.tag == '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}tbl':
p_t_list.append(Table(content, docx._body))
else:
print(content.tag)
return p_t_list
def iterate_items(parent):
""" Обход параграфов и таблиц в документе """
if isinstance(parent, DocumentType):
parent_elem = parent.element.body
elif isinstance(parent, _Cell):
parent_elem = parent._tc # pylint: disable=protected-access
else:
raise ValueError('Oops')
for child in parent_elem.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent)
elif isinstance(child, CT_Tbl):
yield Table(child, parent)
def iter_block_items(file):
"""
获取Word当中的表格及段落并维持其原本的段落顺序.
首先获取docx文档中的每个element
将Paragraph对象的文本提取出来保存在结果列表中
将Table对象保存在结果列表中,Table对象的值需要逐个Cell读取
"""
res = []
for child in file.element.body:
if isinstance(child, CT_P):
res.append(Paragraph(child, Document).text)
elif isinstance(child, CT_Tbl):
res.append(Table(child, Document))
return res
def _get_docx_part_as_text(doc_part):
"""
Get all text components from the given BlockItemContainer.
"""
res_text = ""
for ele in doc_part._element:
if isinstance(ele, CT_Tbl):
tbl = Table(ele, doc_part)
for row in tbl.rows:
for cell in row.cells:
res_text += _get_docx_part_as_text(cell) + "\n"
elif isinstance(ele, CT_P):
res_text += Paragraph(ele, doc_part).text + "\n"
return res_text
def iter_block_items(self, parent):
"""切分document"""
if isinstance(parent, Document): # 是doc
parent_elm = parent.element.body # 返回文档的内容 w:body
elif isinstance(parent, _Cell): # 是表格单元就将表格单元的内容返回
parent_elm = parent._tc # w:tc [table cell]
else:
raise ValueError("something's not right")
for child in parent_elm.iterchildren(): # 迭代子元素，【分割块】
if isinstance(child, CT_P): # 属于w:p
yield Paragraph(child, parent) # 生成器生成段落代理【标记这个块是段落】
elif isinstance(child, CT_Tbl): # 属于w:tb1
yield Table(child, parent) # 生成器生成表格代理【标记这个块是表格】
def iter_block_items(parent):
# print('utils.py ----> iter_block_items:', 2)
if isinstance(parent, dc):
parent_elm = parent.element.body
elif isinstance(parent, _Cell):
parent_elm = parent._tc
else:
raise ValueError("[TypeError] Document in insuitable type.")
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent)
elif isinstance(child, CT_Tbl):
yield Table(child, parent)
def iter_block_items(parent):
if isinstance(parent, Document):
parent_elm = parent.element.body
elif isinstance(parent, _Cell):
parent_elm = parent._tc
else:
raise ValueError("sth's wrong")
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent)
elif isinstance(child, CT_Picture):
yield InlineShape(child, parent)
elif isinstance(child, CT_Tbl):
yield Table(child, parent)
def iter_block_items(parent):
# Reads and stores text in parent_elm
if isinstance(parent, _Document):
parent_elm = parent.element.body
# Reads and stores tables in parent_elm
elif isinstance(parent, _Cell):
parent_elm = parent._tc
else:
raise ValueError("something's not right")
for child in parent_elm.iterchildren():
if isinstance(child, CT_P):
yield Paragraph(child, parent)
elif isinstance(child, CT_Tbl):
yield Table(child, parent)