admin/GoogleScrape
1
0
Fork 0
mirror of https://github.com/timberjoegithub/GoogleScrape.git synced 2026-07-22 00:19:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

working on xls transformation

Browse Source
This commit is contained in:
Joe Steele
2024-06-19 08:02:43 -04:00
parent a8c86b45ec
commit 239c3a5434
1 changed files with 20 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
social.py
+20 -2
View File
@@ -164,6 +164,18 @@ def get_auth_connect():
connections |= {'xlsdf':xls_wb_df,'data':ws,'datawb':wb} connections |= {'xlsdf':xls_wb_df,'data':ws,'datawb':wb}
# connections.update({'data':ws}) # connections.update({'data':ws})
# connections.update({'datawb':wb}) # connections.update({'datawb':wb})
sheet = wb.active
c_row = sheet.max_row
c_column = sheet.max_column
out_data=[]
local_dict={}
for a in range(1, c_row + 1):
for b in range(1, c_column + 1):
ob = sheet.cell(row=a, column=b)
local_dict[b] = ob.value
out_data.append(str(local_dict))
connections['xls_list'] = out_data
if env.instagram: if env.instagram:
print(' Connecting to Instagram ...') print(' Connecting to Instagram ...')
instasessionclient = instagrapi.Client() instasessionclient = instagrapi.Client()
@@ -1414,13 +1426,19 @@ def process_reviews2(outputs):
# Process # Process
webcount = xtwittercount = instagramcount = facebookcount = 0 webcount = xtwittercount = instagramcount = facebookcount = 0
# webcount=xtwittercount=instagramcount=yelpcount=threadscount=facebookcount=tiktokcount = 0 # webcount=xtwittercount=instagramcount=yelpcount=threadscount=facebookcount=tiktokcount = 0
if env.datasource == 'xls': if env.datasource == 'db':
cols2 = ["num","name", "comment", 'rating','picsURL','picsLocalpath','source','date',
'address','dictPostComplete']
rows_orig = list(outputs['data'].iter_rows(min_row=1, max_row=outputs['data'].max_row)) rows_orig = list(outputs['data'].iter_rows(min_row=1, max_row=outputs['data'].max_row))
rows_orig2 = list(outputs['xlsdf'].iter_rows(min_row=1, max_row=outputs['xlsdf'].max_row)) ttt = list(outputs['data'].iter_rows(min_row=1, max_row=outputs['data'].max_row))
ows_orig = list(outputs['data'])
rows_orig2 = list(outputs['xlsdf'].values)
rows3 = outputs['data'].iter_rows(min_row=1, max_row=outputs['data']) rows3 = outputs['data'].iter_rows(min_row=1, max_row=outputs['data'])
rows4 = pd.DataFrame(outputs['xlsdf']) rows4 = pd.DataFrame(outputs['xlsdf'])
rows5 = pd.DataFrame(outputs['posts']) rows5 = pd.DataFrame(outputs['posts'])
rows6 = pd.DataFrame(outputs['data']) rows6 = pd.DataFrame(outputs['data'])
# df2 = pd.DataFrame(outputs['xlsdf'].values, columns=cols2).iter_rows(min_row=1, max_row=outputs['data'].max_row)
# df3 = pd.DataFrame(outputs['xlsdf'].iter_rows(min_row=1, max_row=outputs['data'].max_row))
# rows = [({0:p.id},{1:p.name}, { 2:p.comment}, {3: p.rating}, {4:p.picsURL},\ # rows = [({0:p.id},{1:p.name}, { 2:p.comment}, {3: p.rating}, {4:p.picsURL},\
# {5:p.picsLocalpath},{6:p.source},{7:p.date},{8:p.address},{9:p.dictPostComplete})\ # {5:p.picsLocalpath},{6:p.source},{7:p.date},{8:p.address},{9:p.dictPostComplete})\
# for p in rows_orig] # for p in rows_orig]