def fasterSolution(self, b):
self.progress['value'] = time.time() - self.start_time
self.progress.update()
self.document = Document()
self.COLUMNS = 4
self.ROWS = 1000
self.table = self.document.add_table(rows=self.ROWS,
cols=self.COLUMNS)
self.table_cells = self.table._cells
for i in range(self.ROWS):
self.row_cells = self.table_cells[i * self.COLUMNS:(i + 1) *
self.COLUMNS]
for cell in self.row_cells:
self.paragraph = cell.paragraphs[0]
self.run = self.paragraph.add_run()
self.run.add_picture(self.folderAddress + "\\" + self.b +
".png",
width=350000 * 0.71,
height=350000 * 0.49)
self.progress['value'] = time.time() - self.start_time
self.progress.update()
self.document.save(self.folderAddress + "\\" + "singleFolder" +
"\\" + self.b + "_" + str(1) + ".docx")
self.progress['value'] = time.time() - self.start_time
self.progress.update()
def it_has_part_as_header_part(self):
document = Document(dir_pkg_path)
header = document.add_header()
paragraph = header.add_paragraph()
run = paragraph.add_run()
run.add_floating_picture(python_powered_path)
document.save('/home/daniel/faboozle.docx')
def it_removes_header_part(self):
document = Document(dir_pkg_path)
document.remove_headers()
for rel_id, part in document.part.related_parts.items():
assert part.content_type != CT.WML_HEADER
header_elm_tag = 'w:headerReference'
sentinel_sectPr = document._body._body.get_or_add_sectPr()
header_elms = sentinel_sectPr.findall(qn(header_elm_tag))
assert len(header_elms) == 0
def it_removes_header_part(self):
document = Document(dir_pkg_path)
document.remove_headers()
for rel_id, part in document.part.related_parts.items():
assert part.content_type != CT.WML_HEADER
header_elm_tag = 'w:headerReference'
sentinel_sectPr = document._body._body.get_or_add_sectPr()
header_elms = sentinel_sectPr.findall(qn(header_elm_tag))
assert len(header_elms) == 0
def it_removes_footer_part(self):
document = Document(dir_pkg_path)
document.remove_footers()
for rel_id, part in document.part.related_parts.items():
assert part.content_type != CT.WML_FOOTER
footer_elm_tag = "w:footerReference"
sentinel_sectPr = document._body._body.get_or_add_sectPr()
footer_elms = sentinel_sectPr.findall(qn(footer_elm_tag))
assert len(footer_elms) == 0
def fasterSolution(folderAddress, pic):
document = Document()
COLUMNS = 4
table = document.add_table(rows=1000, columns=COLUMNS)
table_cells = table._cells
for i in range(ROWS):
row_cells = table_cells[i * COLUMNS:(i + 1) * COLUMNS]
for cell in row_cells.cells:
paragraph = cell.paragraphs[0]
run = paragraph.add_run()
run.add_picture(folderAddress + pic + ".png",
width=350000 * 1.42,
height=700000 * 0.49)
def finalizer(filed=[]):
files = [
"static/merge/planning and organising.docx",
"static/merge/customer service.docx", "static/merge/leadership.docx",
"static/merge/commercial awareness.docx",
"static/merge/initiative.docx",
"static/merge/persuasive oral communication.docx"
]
output_doc = Document("static/merge/nicopon.docx")
for file in filed:
if file in files:
pass
else:
files.append(file)
for index, file in enumerate(files):
try:
input_doc = Document(file)
paro = 0
if index < len(files):
output_doc.add_page_break()
for para in input_doc.paragraphs:
get_para_data(output_doc, para, paro)
paro += 1
except Exception as e:
print("mhhh")
print(e)
p = output_doc.add_paragraph()
r = p.add_run()
r.add_picture('static/end.PNG', width=Inches(7.09), height=Inches(8.76))
output_doc.save('static/merge/report.docx')
def it_adds_to_doc_without_header(self):
document = Document(dir_pkg_path)
header = document.add_header()
header_elm_tag = 'w:headerReference'
sentinel_sectPr = document._body._body.get_or_add_sectPr()
header_elms = sentinel_sectPr.findall(qn(header_elm_tag))
assert len(header_elms) == 1
assert header
assert len(header.paragraphs) == 0
header.add_paragraph('foobar')
assert len(header.paragraphs) == 1
def putIntoDocumentFiles(folderAddress, pic):
document = Document()
table = document.add_table(rows=100, cols=4) #ROWS=25 For 100 barcodes
for row in table.rows:
for cell in row.cells:
paragraph = cell.paragraphs[0]
run = paragraph.add_run()
run.add_picture(
folderAddress + "\\" + pic + ".png",
width=350000 * 0.71,
height=350000 * 0.49
) #(width,height)=>dimensions(singleTableRow,singleTableColumn) for singlePage
document.save(folderAddress + "\\singleFolder" + "\\" + pic + "_" +
"1" + ".docx")
def it_adds_to_doc_without_footer(self):
document = Document(dir_pkg_path)
document.remove_footers()
footer = document.add_footer()
footer_elm_tag = 'w:footerReference'
sentinel_sectPr = document._body._body.get_or_add_sectPr()
footer_elms = sentinel_sectPr.findall(qn(footer_elm_tag))
assert len(footer_elms) == 1
assert footer
assert len(footer.paragraphs) == 0
footer.add_paragraph('foobar')
assert len(footer.paragraphs) == 1
def it_adds_to_doc_without_footer(self):
document = Document(dir_pkg_path)
document.remove_footers()
footer = document.add_footer()
footer_elm_tag = "w:footerReference"
sentinel_sectPr = document._body._body.get_or_add_sectPr()
footer_elms = sentinel_sectPr.findall(qn(footer_elm_tag))
assert len(footer_elms) == 1
assert footer
assert len(footer.paragraphs) == 0
footer.add_paragraph("foobar")
assert len(footer.paragraphs) == 1
def add_picture_fixture(self, request, run_, picture_):
document = Document()
image_path_ = instance_mock(request, str, name='image_path_')
width, height = 100, 200
class_mock(request, 'docx.text.Run', return_value=run_)
run_.add_picture.return_value = picture_
return (document, image_path_, width, height, run_, picture_)
def get_grouplist(self, filename):
doc = Document(filename)
table = doc.tables[0]
# Data will be a list of rows represented as dictionaries
# containing each row's data.
data = []
keys = None
for i, row in enumerate(table.rows):
text = (cell.text for cell in row.cells)
# Establish the mapping based on the first row
# headers; these will become the keys of our dictionary
if i == 0:
keys = tuple(text)
continue
# Construct a dictionary for this row, mapping
# keys to values for this row
row_data = dict(zip(keys, text))
data.append(row_data)
grouplist = []
for dict_ in data:
fio = dict_.get('Фамилия, имя, отчество ')
grouplist.append(fio)
return grouplist
def __init__(
self,
filename,
):
self.filename = filename
self.document = Document(filename)
self.outlist = []
def read_table(docv):
document = Document(docv)
table = document.tables[1]
table_info = document.tables[0]
data = []
info = []
keys = None
for i, row in enumerate(table_info.rows):
text = [cell.text for cell in row.cells]
info.append(text)
for i, row in enumerate(table.rows):
text = (cell.text for cell in row.cells)
tr = [cell.text for cell in row.cells]
hu = len(tr)
if hu == 4:
keys = ("number", "title", "comments", "no")
elif hu == 3:
keys = ("number", "title", "comments")
elif hu == 2:
keys = ("title", "comments")
row_data = dict(zip(keys, text))
data.append(row_data)
info = [info[0][1], info[0][3], info[1][1], info[1][3]]
namer(info[0])
session["inf"] = info
#info candidate,excercise,assesor,date would be good if stored in sessions
return data
def parse():
data = []
dirpath = ent_path.get()
for path in os.listdir():
full_path = os.path.join(dirpath, path)
if os.path.isfile(full_path) and path.endswith(".docx"):
document = Document(full_path)
if len(document.tables) == 0:
continue
table = document.tables[0]
data.append([])
flag = False
for row in table.rows:
for cell in iter_unique_cells(row):
for para in cell.paragraphs:
text = para.text.strip()
if not len(text):
continue
if text[-1] == ':':
data[-1].append('')
flag = True
else:
texts = text.split(':')
if len(texts) == 1 and flag:
data[-1][-1] += text
elif len(texts) > 1:
data[-1].append(texts[1])
flag = False
df = pd.DataFrame(data, columns=keys)
df.to_excel("output.xlsx", index=False)
def it_has_rel_as_footer_rel(self):
document = Document(dir_pkg_path)
footer_rel_exists = False
for rel_id, rel in document.part.rels.items():
if rel.reltype == RT.FOOTER:
footer_rel_exists = True
assert footer_rel_exists
def it_has_rel_as_header_rel(self):
document = Document(dir_pkg_path)
header_rel_exists = False
for rel_id, rel in document.part.rels.items():
if rel.reltype == RT.HEADER:
header_rel_exists = True
assert header_rel_exists
def readDocxParagraph(name): str = '' document = Document(name) for para in document.paragraphs: str = str + para.text + u" endpara " str = str.lower() return str
def add_picture_fixture(self, request, Document_inline_shapes_,
inline_shapes_):
width, height, expected_width, expected_height = request.param
document = Document()
image_path_ = instance_mock(request, str, name='image_path_')
picture_ = inline_shapes_.add_picture.return_value
picture_.width, picture_.height = 200, 100
return (document, image_path_, width, height, inline_shapes_,
expected_width, expected_height, picture_)
def file_tables(f,filename): # returns tables in document
# print("parse files")
document_tables = []
document = Document(f) #currently only supports docx files
for t in document.tables: #m
# print("__ table __ ")
# print(t)
document_tables.append(t)
return document_tables
def it_has_part_as_header_part(self):
document = Document(dir_pkg_path)
header_part_exists = False
for rel_id, part in document.part.related_parts.items():
if part.content_type == CT.WML_HEADER:
header_part_exists = True
assert isinstance(part, XmlPart)
assert header_part_exists
def convert_table_to_df(document_name, table_nos=[]):
document = Document(document_name)
outlist = []
if table_nos == '':
table_nos = list(range(len(document.tables)))
for table in table_nos:
input_table = document.tables[table]
table_dataframe = table_to_df(input_table)
outlist.append(table_dataframe)
return outlist
def __init__(self, context, request=None):
"""Read the docx template and initialize some instance attributes
that will be used to compile the template
"""
self.context = context
self.request = request
self.template = Document(self._template_filename)
self.use_existing_measures = False
self.tool_type = get_tool_type(self.context)
self.tti = getUtility(IToolTypesInfo)
self.italy_special = False
def readDocxTable(name): str = '' document = Document(name) tables = document.tables for table in tables: for row in table.rows: for cell in row.cells: for paragraph in cell.paragraphs: str = str + paragraph.text + u" endpara " str = str.lower() return str
def import_data(filename):
conn = lite.connect("input.db")
cur = conn.cursor()
cur.execute(
"create table IF NOT EXISTS input('id' integer, 'description' text, 'datetime' integer, 'longitute' real, 'latitude' real, 'elevation' integer)"
)
cur.execute("select count(*) from input")
count = cur.fetchall()
if (count[0][0] == 0):
i = 1
document = Document(filename)
paragraph = document.paragraphs[0]
while (len(paragraph.text) != 0):
document = Document(filename)
paragraph = document.paragraphs[i]
col = re.split(r'\t+', paragraph.text)
cur.execute("insert into input values(?,?,datetime(?),?,?,?)",
(col[0], col[1], col[2], col[3], col[4], col[5]))
conn.commit()
i = i + 1
conn.close()
def __init__(self, context, request=None):
"""Read the docx template and initialize some instance attributes
that will be used to compile the template
"""
self.context = context
self.request = request
self.template = Document(self._template_filename)
self.use_existing_measures = api.portal.get_registry_record(
"euphorie.use_existing_measures", default=False)
self.tool_type = get_tool_type(self.webhelpers._survey)
self.tti = getUtility(IToolTypesInfo)
self.italy_special = self.webhelpers.country == "it"
def word_file_data(fileLocation):
document = Document(fileLocation)
table = document.tables[0]
fileContentList = []
for rw in table.rows:
value = rw.cells[0].text
if value == '':
pass
else:
fileContentList.append(value)
print(fileContentList)
return fileContentList
def parse_doc():
if request.method=='POST':
filename=request.files['img']
#print(filename)
txt=list()
logging.getLogger().setLevel(logging.INFO)
logging.info('File Name {}'.format(filename))
fileextens=filename.filename.split('.')[1]
print(fileextens)
if fileextens=='docx':
logging.info('File name ends with docx')
doc=Document(filename)
for para in doc.paragraphs:
txt.append(para.text)
full_t= ' '.join(txt)
name_e=ex.name_extraction(full_t)
session['name_session']=name_e
logging.info('Extracted Name {}'.format(name_e))
mob=ex.extract_mob_number(full_t)
session['mob_session']=mob
logging.info('Extracted Mobile {}'.format(mob))
mail=ex.extract_mail(full_t)
session['mail_session']=mail
logging.info('Extracted mail {}'.format(mail))
print(session.get('mail_session'))
skills=ex.extract_skills(doc)
logging.info('Extracted Skills {}'.format(skills))
session['skills_session']=skills
if not mail or not name_e or not mob or not skills:
txt_doc=ex.txt_extraction(filename)
if not mob:
mob_doc=ex.extract_mob_number(txt_doc)
print(mob_doc)
if not mail:
mail_doc=ex.extract_mail(txt_doc)
print(mail_doc)
if not name_e:
name_doc=ex.name_extraction(txt_doc)
print(name_doc)
if not skills:
url=ex.extract_linkedinurl(txt_doc)
skills=linkedin.skills_linkdn(url)
print(skills)
print("skills")
return "Skills"
return "File Not Uploaded"
def parse_all_docxs_table():
path = './src/data/basket_elective_docxs/'
for filename in os.listdir(path):
# print(filename)
document = Document(path + filename)
#read from docs file
for j in range(len(document.tables)):
table = document.tables[j]
data = []
keys = None
fname = ""
for i, row in enumerate(table.rows):
if i != 0:
text = (cell.text for cell in row.cells)
if i == 1:
keys = tuple(text)
continue
row_data = dict(zip(keys, text))
data.append(row_data)
else:
# pass
text = (cell.text for cell in row.cells)
fname = tuple(text)[0] + '.xlsx'
fname = fname.replace(" ", "_")
fname = fname.replace("/", "_")
fname = fname.replace(":", "_")
fname = './src/tmp/baskets/' + fname
if str(os.path.isfile(fname)) == False:
print(os.path.isfile(fname))
workbook = xlwt.Workbook(fname)
ws = workbook.add_sheet('Tested')
workbook.save(fname)
print(fname, ' is created')
# print(data)
# # print(len(data))
# print(fname)
workbook = xlwt.Workbook(fname)
ws = workbook.add_sheet('Tested')
workbook.save(fname)
wb = openpyxl.Workbook()
sheet = wb.active
sheet.cell(row=1, column=1).value = 'Course code'
sheet.cell(row=1, column=2).value = 'Course name'
sheet.cell(row=1, column=3).value = 'L-T-P-C'
count = 2
for i in range(len(data)):
sheet.cell(row=count, column=1).value = data[i][
'Course code'][:2] + " " + data[i]['Course code'][2:]
sheet.cell(row=count, column=2).value = data[i]['Course name']
sheet.cell(row=count, column=3).value = data[i]['L-T-P-C']
count = count + 1
wb.save(fname)
def fasterSolution(folderAddress, pic, progress):
progress['value'] = time.time() - start_time
progress.update()
document = Document()
COLUMNS = 4
ROWS = 1000
table = document.add_table(rows=ROWS, cols=COLUMNS)
table_cells = table._cells
for i in range(ROWS):
row_cells = table_cells[i * COLUMNS:(i + 1) * COLUMNS]
for cell in row_cells:
paragraph = cell.paragraphs[0]
run = paragraph.add_run()
run.add_picture(folderAddress + "\\" + pic + ".png",
width=350000 * 0.71,
height=350000 * 0.49)
progress['value'] = time.time() - start_time
progress.update()
document.save(folderAddress + "\\" + "singleFolder" + "\\" + pic +
"_" + str(1) + ".docx")
progress['value'] = time.time() - start_time
progress.update()
def it_adds_to_doc_without_header(self):
document = Document(dir_pkg_path)
sentinel_sectPr = document.sections[0]
header_elm_tag = 'w:headerReference'
header = sentinel_sectPr.add_header()
header_elms = sentinel_sectPr.findall(qn(header_elm_tag))
assert len(header_elms) == 1
assert header
assert len(header.paragraphs) == 0
header.add_paragraph('foobar')
assert len(header.paragraphs) == 1
def parse_summary(assignment, file):
document = Document(file)
regex = re.compile("[A-Z][A-Z][A-Z] [0-9][0-9][0-9][0-9]")
course_title = ''
for paragraph in document.paragraphs:
result = regex.match(paragraph.text)
if(result):
course_title = result.group()
break
if assignment:
assignment = assignment.replace('\n', ', ')
summary = course_title + ' ' + assignment
else:
summary = 'N/A'
return summary
def getTable(filename, n=0):
from docx.api import Document
document = Document(filename)
table = document.tables[n]
data = []
keys = None
for i, row in enumerate(table.rows):
text = (cell.text for cell in row.cells)
if i == 0:
keys = tuple(text)
continue
row_data = dict(zip(keys, text))
data.append(row_data)
print(data)
def read_table(docv):
document = Document(docv)
table = document.tables[1]
data = []
keys = None
for i, row in enumerate(table.rows):
text = (cell.text for cell in row.cells)
keys = ("number", "title", "comments", "no")
'''
if i == 0:
keys = tuple(text)
continue'''
row_data = dict(zip(keys, text))
data.append(row_data)
return data
def it_should_raise_if_not_a_Word_file(self, Package_, package_, docx_):
package_.main_document.content_type = 'foobar'
with pytest.raises(ValueError):
Document._open(docx_)
def it_opens_default_template_if_no_file_provided(
self, Package_, default_docx_):
Document._open(None)
Package_.open.assert_called_once_with(default_docx_)
def it_can_open_a_docx_file(self, open_fixture):
docx_, Package_, package_, document_part_ = open_fixture
document_part, package = Document._open(docx_)
Package_.open.assert_called_once_with(docx_)
assert document_part is document_part
assert package is package_
