def annotations_from_xlsx(xslxfile, delimiter='\t', rm_csv=False):
"""Read annotations from xlsx file.
xlsx is converted to csv file and than parsed with csv reader.
"""
csvfile = "{}.csv".format(xslxfile)
pyexcel.save_as(file_name=xslxfile, dest_file_name=csvfile, dest_delimiter=delimiter)
res = ModelAnnotator.annotations_from_csv(csvfile, delimiter=delimiter)
if rm_csv:
import os
os.remove(csvfile)
return res
def create_sample_file1(file):
data = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 1.1, 1]
table = []
table.append(data[:4])
table.append(data[4:8])
table.append(data[8:12])
pyexcel.save_as(dest_file_name=file, array=table)
def save_to_database(
self,
session=None, table=None, initializer=None, mapdict=None,
auto_commit=True,
**keywords):
"""
Save data from a sheet to database
:param session: a SQLAlchemy session
:param table: a database table
:param initializer: a custom table initialization function if you have one
:param mapdict: the explicit table column names if your excel data do not have the exact column names
:param keywords: additional keywords to :meth:`pyexcel.Sheet.save_to_database`
"""
params = self.get_params(**keywords)
if 'name_columns_by_row' not in params:
params['name_columns_by_row'] = 0
if 'name_rows_by_column' not in params:
params['name_rows_by_column'] = -1
params['dest_session']=session
params['dest_table'] = table
params['dest_initializer']=initializer
params['dest_mapdict'] = mapdict
params['dest_auto_commit']=auto_commit
pe.save_as(**params)
def setUp(self):
"""
Make a test csv file as:
1, 2, 3, 4
5, 6, 7, 8
9, 10, 11, 12
"""
self.testfile1 = "testcsv1.csv"
content = [
[1, 'a'],
[2, 'b'],
[3, 'c'],
[4, 'd'],
[5, 'e'],
[6, 'f'],
[7, 'g'],
[8, 'h']
]
pe.save_as(dest_file_name=self.testfile1,
array=content)
self.testfile2 = "testcsv2.csv"
content = [
[1, 'a', 'c'],
[2, 'b', 'h'],
[3, 'c', 'c'],
[8, 'h', 'd']
]
pe.save_as(dest_file_name=self.testfile2,
array=content)
def create_sample_file1(file):
data = ["a", "b", "c", "d", "e", "f", "g", "h", "i", "j", 1.1, 1]
table = []
table.append(data[:4])
table.append(data[4:8])
table.append(data[8:12])
pyexcel.save_as(array=table, dest_file_name=file)
def setUp(self):
self.excel_filename = "testdateformat.csv"
self.data = [[
datetime.date(2014,12,25),
datetime.datetime(2014,12,25,11,11,11),
datetime.datetime(2014,12,25,11,11,11,10)
]]
pe.save_as(dest_file_name=self.excel_filename, array=self.data)
def setUp(self):
self.data = {
"1": [1, 2, 3, 4, 5, 6, 7, 8],
"3": [1.1, 2.2, 3.3, 4.4, 5.5, 6.6, 7.7, 8.8],
"5": [2, 3, 4, 5, 6, 7, 8, 9],
}
self.testfile = "test.xls"
pe.save_as(dest_file_name=self.testfile, adict=self.data)
def test_writing_multiline_ods():
content = "2\n3\n4\n993939\na"
testfile = "writemultiline.ods"
array = [[content, "test"]]
pyexcel.save_as(array=array, dest_file_name=testfile)
sheet = pyexcel.get_sheet(file_name=testfile)
assert sheet[0, 0] == content
os.unlink(testfile)
def test_new_normal_usage(self):
content = [
[1, 2, 3],
[4, 588, 6],
[7, 8, 999]
]
pe.save_as(array=content, dest_file_name=self.testfile)
self._check_test_file('new_normal_usage')
def test_new_normal_usage_irregular_columns(self):
content = [
[1, 2, 3],
[4, 588, 6],
[7, 8]
]
pe.save_as(array=content, dest_file_name=self.testfile)
self._check_test_file('new_normal_usage_irregular_columns')
def test_issue_10(self):
thedict = OrderedDict()
thedict.update({"Column 1": [1,2,3]})
thedict.update({"Column 2": [1,2,3]})
thedict.update({"Column 3": [1,2,3]})
pe.save_as(adict=thedict, dest_file_name="issue10.xls")
newdict = pe.get_dict(file_name="issue10.xls")
assert isinstance(newdict, OrderedDict) == True
assert thedict == newdict
def test_no_title_single_sheet(self):
content = [
[1, 2, 3],
[4, 588, 6],
[7, 8, 999]
]
pe.save_as(array=content, dest_file_name=self.testfile, dest_write_title=False)
self._check_test_file('no_title_single_sheet')
def test_save_as_to_database(self):
adict = {
"X": [1, 4],
"Y": [2, 5],
"Z": [3, 6]
}
pe.save_as(adict=adict, dest_session=self.session, dest_table=Signature)
result = pe.get_dict(session=self.session, table=Signature)
assert adict == result
def test_save_as_and_append_colnames(self):
data = [[1, 2, 3], [4, 5, 6]]
sheet = pe.Sheet(data)
testfile = "testfile.xls"
testfile2 = "testfile.xls"
sheet.save_as(testfile)
pe.save_as(file_name=testfile, out_file=testfile2, colnames=["X", "Y", "Z"])
array = pe.get_array(file_name=testfile2)
assert array == [["X", "Y", "Z"], [1, 2, 3], [4, 5, 6]]
def CVSOutput(self,sortedTempSimilarityTuple):
data = []
for item in sortedTempSimilarityTuple:
dataTuple = []
relations = item[0].split("-")
dataTuple.append(relations[0])
dataTuple.append(relations[1])
dataTuple.append(item[1])
data.append(dataTuple)
pyexcel.save_as(array = data, dest_file_name = 'testCSV.csv')
def test_new_normal_usage(self):
content = [
[1, 2, 3],
[4, 588, 6],
[7, 8, 999]
]
pe.save_as(array=content, dest_file_name=self.testfile)
with open(self.testfile, "r") as f:
written_content = json.load(f)
assert written_content == content
def test_mapping_array(self):
data2 = [
["A", 1, 4],
["B", 2, 5],
["C", 3, 6]
]
mapdict = ["X", "Y", "Z"]
model=FakeDjangoModel()
pe.save_as(array=data2, dest_model=model, dest_mapdict=mapdict, transpose_before=True)
assert model.objects.objs == self.result
def test_mapping_array(self):
data2 = [
["A", "B", "C"],
[1, 2, 3],
[4, 5, 6]
]
mapdict = ["X", "Y", "Z"]
model=FakeDjangoModel()
pe.save_as(array=data2, dest_model=model, dest_mapdict=mapdict)
assert model.objects.objs == self.result
def setUp(self):
self.data = {
"1": [1, 2, 3, 4, 5, 6, 7, 8],
"2": ["1", "2", "3", "4", "5", "6", "7", "8"],
"3": [1.1, 2.2, 3.3, 4.4, 5.5, 6.6, 7.7, 8.8],
"4": ["1.1", "2.2", "3.3", "4.4", "5.5", "6.6", "7,7", "8.8"],
"5": [2, 3, 4, 5, 6, 7, 8, 9],
"6": ["2", "3", "4", "5", "6", "7", "8", "9"]
}
self.testfile = "test.xls"
pe.save_as(dest_file_name=self.testfile, adict=self.data)
def test_data_frame(self):
content = [
["", "Column 1", "Column 2", "Column 3"],
["Row 1", 1, 2, 3],
["Row 2", 4, 5, 6],
["Row 3", 7, 8, 9]
]
pe.save_as(array=content, name_rows_by_column=0, name_columns_by_row=0,
dest_file_name=self.testfile)
self._check_test_file('data_frame')
def setUp(self):
self.testfile = "test.xlsm"
self.content = [
["X", "Y", "Z"],
[1, 2, 3],
[1, 2, 3],
[1, 2, 3],
[1, 2, 3],
[1, 2, 3]
]
pe.save_as(dest_file_name=self.testfile, array=self.content)
def test_csvbook_irregular_columns(self):
content = [
[1, 2, 3],
[4, 588, 6],
[7, 8]
]
self.testfile2 = "testfile.csv"
pe.save_as(array=content, dest_file_name=self.testfile2)
pe.save_as(file_name=self.testfile2, dest_file_name=self.testfile)
self._check_test_file('csvbook_irregular_columns')
def test_row_series(self):
content = [
["Row 1", 1, 2, 3],
["Row 2", 4, 5, 6],
["Row 3", 7, 8, 9]
]
pe.save_as(array=content, name_rows_by_column=0,
dest_file_name=self.testfile)
self._check_test_file('row_series')
def test_column_series_irregular_columns(self):
content = [
["Column 1", "Column 2", "Column 3"],
[1, 2, 3],
[4, 5, 6],
[7, 8]
]
pe.save_as(array=content, name_columns_by_row=0,
dest_file_name=self.testfile)
self._check_test_file('column_series_irregular_columns')
def test_save_file_as_another_one(self):
data = [["X", "Y", "Z"], [1, 2, 3], [4, 5, 6]]
sheet = pe.Sheet(data)
testfile = "testfile.xls"
testfile2 = "testfile2.csv"
sheet.save_as(testfile)
pe.save_as(file_name=testfile, out_file=testfile2)
sheet = pe.get_sheet(file_name=testfile2)
sheet.format(int)
assert sheet.to_array() == data
os.unlink(testfile)
os.unlink(testfile2)
def setUp(self):
self.testfile = "test.xlsm"
self.content = {
'Series_6': ['', '', '', '', '', 6.0],
'Series_5': ['', '', '', '', '', 5.0, 5.0, '', '', ''],
'Series_4': ['', '', '', 4.0, 4.0, 4.0, '', '', '', 4.0, 4.0],
'Series_3': ['', '', 3.0, 3.0, 3.0, 3.0, '', '', 3.0, 3.0, 3.0],
'Series_2': ['', 2.0, 2.0, 2.0, 2.0, 2.0],
'Series_1': [1.0]
}
pe.save_as(dest_file_name=self.testfile,
adict=self.content)
def test_write_texttable():
content = [[1,2]]
test_file = "test.texttable"
expected = dedent("""
pyexcel_sheet1:
+---+---+
| 1 | 2 |
+---+---+""").strip('\n')
pe.save_as(array=content, dest_file_name=test_file)
with open(test_file, 'r') as f:
written = f.read()
eq_(written, expected)
os.unlink(test_file)
def test_new_normal_usage(self):
content = [
[1, 2, 3],
[4, 588, 6],
[7, 8, 999]
]
pe.save_as(array=content, dest_file_name=self.testfile)
f = open(self.testfile, "r")
written_content = f.read()
f.close()
content = dedent("""
[[1, 2, 3], [4, 588, 6], [7, 8, 999]]""").strip('\n')
assert written_content == content
def test_writing_date_format(self):
excel_filename = "testdateformat.xls"
data = [[datetime.date(2014, 12, 25),
datetime.time(11, 11, 11),
datetime.datetime(2014, 12, 25, 11, 11, 11)]]
pe.save_as(dest_file_name=excel_filename, array=data)
r = pe.Reader(excel_filename)
assert isinstance(r[0, 0], datetime.date) is True
assert r[0, 0].strftime("%d/%m/%y") == "25/12/14"
assert isinstance(r[0, 1], datetime.time) is True
assert r[0, 1].strftime("%H:%M:%S") == "11:11:11"
assert isinstance(r[0, 2], datetime.date) is True
assert r[0, 2].strftime("%d/%m/%y %H:%M:%S") == "25/12/14 11:11:11"
os.unlink(excel_filename)
def test_writing_date_format(self):
excel_filename = "testdateformat.xlsx"
data = [[datetime.date(2014,12,25),
datetime.time(11,11,11),
datetime.datetime(2014,12,25,11,11,11)]]
pe.save_as(dest_file_name=excel_filename, array=data)
r = pe.get_sheet(file_name=excel_filename, library="openpyxl")
assert isinstance(r[0,0], datetime.date) == True
assert r[0,0].strftime("%d/%m/%y") == "25/12/14"
assert isinstance(r[0,1], datetime.time) == True
assert r[0,1].strftime("%H:%M:%S") == "11:11:11"
assert isinstance(r[0,2], datetime.date) == True
assert r[0,2].strftime("%d/%m/%y") == "25/12/14"
os.unlink(excel_filename)
def write_to_excel3(data, file_full_name):
pyexcel.save_as(records=data, dest_file_name=file_full_name)
import pyexcel
from collections import OrderedDict
url = "http://s.cafef.vn/bao-cao-tai-chinh/VNM/IncSta/2017/3/0/0/ket-qua-hoat-dong-kinh-doanh-cong-ty-co-phan-sua-viet-nam.chn"
conn = urlopen(url)
raw_data = conn.read()
page_content = raw_data.decode("utf8")
soup = BeautifulSoup(page_content, "html.parser")
div = soup.find(
"div", style="overflow:hidden;width:100%;border-bottom:solid 1px #cecece;")
table = div.find("table", id="tableContent")
tr_list = table.find_all("tr")
news_list = []
for t in tr_list:
td_list = t.find_all("td")
kq = {}
for i in range(len(td_list)):
if td_list[i].string != None:
if i == 0:
kq["Hạng mục"] = td_list[i].string.strip()
elif i == 1:
kq["Qúy 4-2016"] = td_list[i].string.strip()
elif i == 2:
kq["Quý 1-2017"] = td_list[i].string.strip()
elif i == 3:
kq["Quý 2-2017"] = td_list[i].string.strip()
elif i == 4:
kq["Quý 3-2017"] = td_list[i].string.strip()
if kq != {}:
news_list.append(kq)
pyexcel.save_as(records=news_list, dest_file_name="Ketqua.xlsx")
import pyexcel
from collections import OrderedDict
data = [
OrderedDict({
'name': 'quan',
'age': '22',
'city': 'hanoi'
}),
OrderedDict({
'name': 'Hong',
'age': '19',
'city': 'campuchia'
}),
OrderedDict({
'name': 'an',
'age': '18',
'city': 'laos'
})
]
pyexcel.save_as(records=data, dest_file_name="asdfgh.xlsx")
item_content = {
"picture_link": picture_link,
"title": title,
"source": source
}
new_item.append(item_content)
# for pile in block2:
# pile1 = pile.find_all("article","c-article c-article--summary")
# for pile2 in pile1:
# pile3 = pile2.find("div","c-article__container")
# pile4 = pile3.find("div","c-article__image")
# pile5 = pile3.find("div","c-article__summary")
# pile6 = pile4.a
# picture_link = url+ pile6["href"]
# pile7 = pile5.h3
# title = pile7.text
# pile8 = pile7.a
# source = url+ pile8["href"]
# item_content = {
# "source": source,
# "picture_link":picture_link,
# "title":title
# }
# new_item.append(item_content)
pyexcel.save_as(records=new_item, dest_file_name="treehugger_right_craw.xlsx")
for filename in input_files:
# 간혹 xlsx 파일이 아닌 파일이 섞여있을 수 있습니다. 이걸 걸러냅니다.
if ".xlsx" not in filename:
continue
# 엑셀 파일이 맞다면, 파일을 리스트 형태로 읽어옵니다.
file = px.get_array(file_name=directory + "/" + filename)
# 엑셀 파일의 첫 번째 열, 그러니까 헤더만 불러옵니다.
header = file[0]
# 불러온 파일의 헤더가 템플릿과 일치하는지 분석합니다.
if HEADER != header:
# 일치하지 않는다면 건너뛰어버립시다
continue
# CONTENTS 리스트에 엑셀 파일의 내용물을 입력합니다.
CONTENTS += file[1:]
# 합쳐진 엑셀 파일을 저장합니다.
px.save_as(array=CONTENTS, dest_file_name="merged_FILE.xlsx")
# 총 몇개의 파일이 합쳐졌는지를 출력합니다.
print("Total " + str(len(CONTENTS) - 1) + " files were merged.")
# 작업 종료 메시지를 출력합니다.
print("Process Done.")
# 작업에 총 몇 초가 걸렸는지 출력합니다.
end_time = time.time()
print("The Job Took " + str(end_time - start_time) + " seconds.")
# print(text)
# dan_tri_file = open("dantri.html","w")
# dan_tri_file.write(text)
# dan_tri_file.close()
#2 find ROI
soup = BeautifulSoup(text, "html.parser")
# print(soup.prettify())
ul = soup.find("ul", "ul1 ulnew")
# print(ul.prettify())
li_list = ul.find_all("li")
item_list = []
for li in li_list:
# print(li.prettify())
a = li.h4.a
title = a.string #string or content
link = url + a['href']
# print(title)
# print(link)
item = {
"Title": title,
"Link": link,
}
item_list.append(item)
pyexcel.save_as(records=item_list, dest_file_name="dantri.xlsx")
def _create_a_file(self, file):
pyexcel.save_as(dest_file_name=file, array=self.content)
import pyexcel
from urllib.request import urlopen
from bs4 import BeautifulSoup
from collections import OrderedDict
url = "http://s.cafef.vn/bao-cao-tai-chinh/VNM/IncSta/2017/3/0/0/ket-qua-hoat-dong-kinh-doanh-cong-ty-co-phan-sua-viet-nam.chn"
conn = urlopen(url)
raw_data = conn.read()
content = raw_data.decode("utf8")
# f = open("vinamilk.html", "wb")
# f.write(raw_data)
# f.close()
soup = BeautifulSoup(content, "html.parser")
table = soup.find("table", id="tableContent")
tr_list = table.find_all("tr")
table_list = []
for tr in tr_list:
td_list = tr.find_all("td", "b_r_c")
for td in td_list:
td = td.string
data = {"": td}
table_list.append(OrderedDict(data))
pyexcel.save_as(records=table_list, dest_file_name="vinamilk.xlsx")
def test_issue_92_verify_save_as():
records = [{"a": 1, "b": 2, "c": 3}, {"b": 2}, {"c": 3}]
csv_io = p.save_as(records=records, dest_file_type="csv")
content = "a,b,c\r\n1,2,3\r\n,2,\r\n,,3\r\n"
eq_(csv_io.getvalue(), content)
input_driver = input("What is the driver associated with this device? ")
d = {"IP": input_ip, "driver": input_driver}
return d
## This code is left turned off, but might help visualize how pyexcel works with data sets.
## IP is the first column, whereas driver is the second column.
## mylistdict = [ {"IP": "172.16.2.10", "driver": "arista_eos"}, {"IP": "172.16.2.20", "driver": "arista_eos"} ]
## pyexcel.save_as(records=mylistdict, dest_file_name="ip_list.xls")
# Runtime
mylistdict = [] # this will be our list we turn into a *.xls file
print("Hello! This program will make you a *.xls file")
while (True):
mylistdict.append(
get_ip_data()
) # add an item to the list returned by get_ip_data() {"IP": value, "driver": value}
keep_going = input(
"\nWould you like to add another value? Enter to continue, or enter 'q' to quit: "
)
if (keep_going.lower() == 'q'):
break
filename = input("\nWhat is the name of the *.xls file? ")
pyexcel.save_as(records=mylistdict, dest_file_name=filename)
print("The file " + filename + ".xls should be in your local directory")
raw_data = conn.read()
page_content = raw_data.decode("utf8")
soup = BeautifulSoup(page_content, "html.parser")
section = soup.find("section", "section chart-grid")
div = section.find("div", "section-content")
ul = div.find("ul")
li_list = ul.find_all("li")
top_songs = []
for li in li_list:
h3 = li.h3.a
h4 = li.h4.a
name = h3.string
singer = h4.string
song = OrderedDict({"Song": name, "composer": singer})
top_songs.append(song)
pyexcel.save_as(records=top_songs, dest_file_name="itunes.xlsx")
#-------------------------------------------------------------------------------------------
a = top_songs[1]
options = {'default_search': 'ytsearch', 'max_downloads': 1}
dl = YoutubeDL(options)
dl.download(a)
def test_get_dict_from_memory(self):
data = [["X", "Y", "Z"], [1, 2, 3], [4, 5, 6]]
content = pe.save_as(dest_file_type="xls", array=data)
adict = pe.get_dict(file_content=content.getvalue(), file_type="xls")
assert adict == {"X": [1, 4], "Y": [2, 5], "Z": [3, 6]}
def test_get_sheet_from_file_stream(self):
data = [["X", "Y", "Z"], [1, 2, 3], [4, 5, 6]]
content = pe.save_as(dest_file_type="xls", array=data)
sheet = pe.get_sheet(file_stream=content, file_type="xls")
assert sheet.to_array() == data
#copy and save
li_list = ul.find_all("li")
new_list = []
for li in li_list:
h3 = li.h3
a = h3.a
title = a.string
h4 = li.h4
a = h4.a
artist = a.string
songs = {
"title": title,
"artist": artist,
}
new_list.append(songs)
pyexcel.save_as(records=new_list, dest_file_name="demo.xlsx")
#dowload youtube
options = {
"default_search": "ytsearch",
"max_dowload": 100,
"format": "bestaudio/audio",
}
dl = YoutubeDL(options)
# for i in new_list:
# key = i["title"]
# print(key)
# dl.download([key])
for i in new_list:
print(i["title"])
dl.download(i["title"])
def test_series_table(self):
pyexcel.save_as(adict=self.content, dest_file_name=self.testfile)
r = pyexcel.get_sheet(file_name=self.testfile, name_columns_by_row=0)
eq_(r.dict, self.content)
from collections import OrderedDict
url = "https://www.apple.com/itunes/charts/songs"
conn = urlopen(url)
raw_data = conn.read()
page_content = raw_data.decode("utf-8")
soup = BeautifulSoup(page_content, "html.parser")
ul = soup.find("ul", "")
li_list = ul.find_all("li")
itune_list = []
for li in li_list:
a = li.a
h3 = li.h3
h4 = li.h4
Baihat = h3.string
Casi = h4.string
link = url + a["href"]
itune = OrderedDict({
"Baihat": Baihat,
"Casi": Casi,
"link": link,
})
itune_list.append(itune)
pyexcel.save_as(records=itune_list, dest_file_name="Itunes_top_song.xlsx")
def _create_a_file(self, file):
pyexcel.save_as(
dest_file_name=file,
array=self.content,
dest_library="pyexcel-odsw",
)
def test_get_array_from_memory(self):
content = pe.save_as(dest_file_type="xls", array=self.test_data)
array = pe.get_array(file_content=content.getvalue(), file_type="xls")
eq_(array, self.test_data)
import pyexcel
a_list_of_dic = [{"name": "Hieu", "age ": 20}, {"name": "ha", "age ": 20}]
pyexcel.save_as(records=a_list_of_dic, dest_file_name="a1.xlsx")
import pyexcel
# make sure you had pyexcel-xls installed
a_list_of_dictionaries = [{
"Name": 'Adam',
"Age": 28
}, {
"Name": 'Beatrice',
"Age": 29
}, {
"Name": 'Ceri',
"Age": 30
}, {
"Name": 'Dean',
"Age": 26
}]
pyexcel.save_as(records=a_list_of_dictionaries,
dest_file_name="your_file.xlsx")
import pyexcel
# 1. Prepare data
data = [
{
"name": "Son",
"age": 23,
},
{
"name": "Trung",
"age": 19,
},
{
"name": "Dung",
"age": 21,
},
]
# 2. Save
pyexcel.save_as(records=data, dest_file_name="sample.xlsx" )
site_visits = settings.MONGO_DB.instances.aggregate([{"$match":{"fs_site": str(site.id)}}, { "$group" : {
"_id" :
{ "$substr": [ "$start", 0, 10 ] }
}
}])['result']
site_row[-1] = rejected_count
site_row[-2] = flagged_count
site_row[-3] = submission_count
site_row[-4] = len(site_visits)
data.append(site_row)
p.save_as(array=data, dest_file_name="media/stage-report/{}_stage_data.xls".format(project.id))
xl_data = open("media/stage-report/{}_stage_data.xls".format(project.id), "rb")
#Its only quick fix for now, save it in aws bucket whenever possible.
project.progress_report = xl_data.name
project.save()
count += 1
except Exception as e:
print 'Report Gen Unsuccesfull. %s' % e
print e.__dict__
self.stdout.write('Created "%s " report for projects with success!' % (count))
print datetime.now()
h_data_list = []
table = soup.find(id='tableContent')
row = table.find_all('tr')
row_list = []
for item in h_list:
h_data_list.append(item)
for item in row:
r_list = item.find_all('td','b_r_c')
r_data_list = []
for j in r_list:
j = j.string
r_data_list.append(j)
final= []
for item in row_list:
val__list = []
val = {
"Danh Muc" : item[0]
}
for i in range(len(h_data_list)):
val[h_data_list[i]] = item[1+i]
final.append(val)
pyexcel.save_as(records=final,dest_file_name="vinamlk.xlsx")
def test_get_records_from_memory(self):
data = [["X", "Y", "Z"], [1, 2, 3], [4, 5, 6]]
content = pe.save_as(dest_file_type="xls", array=data)
records = pe.get_records(file_content=content.getvalue(),
file_type="xls")
eq_(records, [{"X": 1, "Y": 2, "Z": 3}, {"X": 4, "Y": 5, "Z": 6}])
soup = BeautifulSoup(text, "html.parser")
# print(soup.prettify())
# 2 Find the ROI
ul_news = soup.find("ul", "ul1 ulnew") # find one
# print(ul_news.prettify())
# 3 Extract data
li_list = ul_news.find_all("li")
# print(li_list)
# list_of_dictionaries
news_items = []
for li in li_list:
a = li.h4.a
link = url + a["href"]
title = a.text
item = {
"Title": title,
"Link": link
}
news_items.append(item)
print(news_items)
# 4 Save data
pyexcel.save_as(records=news_items, dest_file_name="dantri.xlsx")
# html_file.close
# 2: Extract ROI (region of interest)
soup = BeautifulSoup(html, "html.parser")
section = soup.find("section", "section chart-grid")
# print(section.prettify())
# 3: Extract info
songs = []
li_list = section.find_all("li")
for li in li_list:
song = {}
song['name'] = li.h3.string
song['artist'] = li.h4.string
songs.append(song)
pyexcel.save_as(records=songs, dest_file_name="top_song.xlsx")
# ***************************************************************************************************
# Part 2 : Search and download to youtube
from youtube_dl import YoutubeDL
options = {
'default_search':
'ytsearch', # tell download to search instead of directly downloading
'max_download': 1 # tell download to download only the first entry(video)
}
new_song = []
dl = YoutubeDL(options)
for li in li_list:
def test_get_sheet_from_memory(self):
data = [["X", "Y", "Z"], [1, 2, 3], [4, 5, 6]]
content = pe.save_as(dest_file_type="xls", array=data)
sheet = pe.get_sheet(file_content=content.getvalue(), file_type="xls")
assert sheet.to_array() == data
#1.4 Save Html Content
# urlretrieve(url, "dantri.html") #Cách dùng thư viện urlretrive
# f = open('dantri.html','w')
# f.write(html_content)
# f.close
#2. Extract ROI(Region of Interest)
soup = BeautifulSoup(html_content, "html.parser")
# print(soup.prettify()) soup.find_all("a", attrs={"class": "sister"})
ul = soup.find("ul", "ul1 ulnew")
li_list = ul.find_all("li")
list_of_dict = []
for li in li_list:
# print(li.prettify())
# print("* " * 20)
# h4 = li.find("h4")
# a = h4.find("a")
dict1 = {}
a = li.h4.a
dict1["Title"] = a.string
dict1["Link"] = url + a["href"]
list_of_dict.append(dict1)
# print(a.string)
# print("* "* 20)
# print(url + a["href"])
#3. Extract info
pyexcel.save_as(records=list_of_dict, dest_file_name="dantri.xlsx")
def test_out_file_parameter():
try:
pe.save_as(array=[[1]], out_file="b", colnames=["X", "Y", "Z"])
except pe.sources.factory.UnknownParameters as e:
eq_(str(e), 'No parameters found!')
def test_get_sheet_from_memory_compatibility(self):
data = [["X", "Y", "Z"], [1, 2, 3], [4, 5, 6]]
content = pe.save_as(dest_file_type="xls", array=data)
pe.get_sheet(content=content.getvalue(), file_type="xls")