def folder_walker(src_folder, dest_folder, target_height, target_width):
src_fs = open_fs(src_folder)
walker = Walker(filter=['*.jpg'])
for path in walker.files(src_fs):
image_path = os.path.normpath(src_folder + os.sep + path)
process_image(image_path, dest_folder, target_height, target_width)
return None
def run(self):
if self.check_acrons():
for acron in self.acrons:
logging.info("Process acronym: %s" % acron)
walker = Walker(filter=["*.xml"], exclude=["*.*.xml"])
acron_folder = path.join(self.xml_fs.root_path, acron)
for xml in walker.files(fs.open_fs(acron_folder)):
if len(path.iteratepath(xml)) == 2:
logging.info("Process XML: %s" % xml)
issue_folder, pack_name = self.collect_xml(acron, xml)
self.collect_pdf(acron, issue_folder, pack_name)
self.collect_img(acron, issue_folder, pack_name)
else:
return False
def collect_pdf(self, acron, issue_folder, pack_name):
walker = Walker(filter=["*" + pack_name + "*.pdf"], max_depth=2)
pdf_path = path.join(self.pdf_fs.root_path, acron, issue_folder)
for pdf in walker.files(fs.open_fs(pdf_path)):
pdf_path = path.join(acron, issue_folder, path.basename(pdf))
target_pdf_path = path.join(acron, issue_folder, pack_name,
self.rename_pdf_trans_filename(pdf))
self.copy(pdf_path, target_pdf_path, src_fs=self.pdf_fs)
def article_ALL_constructor(source_path: str,
dest_path: str,
in_place: bool = False) -> None:
logger.info("Iniciando Construção dos XMLs")
walker = Walker(filter=["*.xml"], exclude=["*.*.xml"])
list_files_xmls = walker.files(fs.open_fs(source_path))
for file_xml in tqdm(list_files_xmls):
file_xml = source_path + file_xml
try:
article_xml_constructor(file_xml, dest_path, in_place)
except Exception as ex:
logger.info("não foi possível gerar o XML do Arquivo %s: %s",
file_xml, ex)
def collect_img(self, acron, issue_folder, pack_name):
walker = Walker(filter=["*" + pack_name + "*"],
max_depth=2,
exclude_dirs=["html"])
img_path = path.join(self.img_fs.root_path, acron, issue_folder)
for img in walker.files(fs.open_fs(img_path)):
img_path = path.join(acron, issue_folder, path.basename(img))
target_img_path = path.join(acron, issue_folder, pack_name,
path.basename(img))
self.copy(img_path, target_img_path, src_fs=self.img_fs)
def read_data_from_files(file_start):
from fs import open_fs
from fs.walk import Walker
home_fs = open_fs('./')
walker = Walker(filter=[file_start+'*.txt'])
data = []
for path in walker.files(home_fs):
with open('.'+path) as f:
A=np.loadtxt((x.replace('[',' ').replace(']',' ').replace(',',' ') for x in f))
# print(A)
data.append(A)
# else: data_list.append(np.loadtxt(dir_name+"/"+name, skiprows=9))
# pbar.update()
# pbar.close()
return np.array(data)
def index(self, conf):
fs = open_fs(conf['url'])
walker = Walker()
for path in walker.files(fs):
yield Pyfsfile(fs, path)