scottk/wlan-lanforge-scripts
1
0
Fork 0
mirror of https://github.com/Telecominfraproject/wlan-lanforge-scripts.git synced 2025-11-03 20:27:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

lf_pdf_search.py : start of preprocessing the text file before writing out to csv

Browse Source 
Signed-off-by: Chuck SmileyRekiere <chuck.smileyrekiere@candelatech.com>
This commit is contained in:
Chuck SmileyRekiere
2021-06-06 07:47:26 -06:00
parent 34e2dc013b
commit d7d54b0e14
1 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
py-scripts/sandbox/lf_pdf_search.py
View File

@@ -54,7 +54,9 @@ class lf_pdf_search():
self.stdout_log = "" self.stdout_log = ""
self.stderr_log_txt = "" self.stderr_log_txt = ""
self.stderr_log = "" self.stderr_log = ""
self.processed_log_txt = ""
self.dataframe = "" self.dataframe = ""
self.pdf_search_csv = ""
def get_data(self): def get_data(self):
@@ -94,17 +96,19 @@ class lf_pdf_search():
# the data mainupulation may be done in other manners # the data mainupulation may be done in other manners
def datafile_to_dataframe(self): def datafile_to_dataframe(self):
# note the error_bad_lines=False will miss one of the lines # note the error_bad_lines=False will miss one of the lines
delimiter_list = [':']
try: try:
self.dataframe = pd.read_csv(self.stdout_log_txt, delimiter = [':']) self.dataframe = pd.read_csv(self.stdout_log_txt, delimiter = [':'])
#self.dataframe = pd.read_csv(self.stdout_log_txt, sep = ':')
except: except:
print("one of the files may have a SN: in it need to correct ") print("one of the files may have a SN: in it need to correct ")
self.dataframe = pd.read_csv(self.stdout_log_txt, delimiter = ':', error_bad_lines=False) self.dataframe = pd.read_csv(self.stdout_log_txt, delimiter = ':', error_bad_lines=False)
#print(self.dataframe) #print(self.dataframe)
print("saving data to .csv") print("saving data to .csv")
# this removes the extention of .txt # this removes the extention of .txt
pdf_search_csv= self.stdout_log_txt[:-4] self.pdf_search_csv= self.stdout_log_txt[:-4]
pdf_search_csv = pdf_search_csv + ".csv" self.pdf_search_csv = self.pdf_search_csv + ".csv"
pdf_search_csv = self.dataframe.to_csv(pdf_search_csv,mode='w',index=False) self.pdf_search_csv = self.dataframe.to_csv(self.pdf_search_csv,mode='w',index=False)
def main(): def main():