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

Merge branch 'main' of https://github.com/timberjoegithub/GoogleScrape

Browse Source
This commit is contained in:
Joe Steele
2024-06-13 08:51:08 -04:00
parent dfb0d4b6f6 d4c10e064d
commit e2e6175452
1 changed files with 31 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
social.py
+31 -16
View File
@@ -1,10 +1,6 @@
#data #data
import time import time
import os import os
from selenium import webdriver
#from selenium.webdriver.chrome.webdriver import WebDriver
#from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
import re import re
import urllib3 import urllib3
from urllib.request import urlretrieve from urllib.request import urlretrieve
@@ -32,16 +28,19 @@ import instagrapi
#from instagrapi.story import StoryBuilder #from instagrapi.story import StoryBuilder
from moviepy.editor import VideoFileClip, concatenate_videoclips from moviepy.editor import VideoFileClip, concatenate_videoclips
#import moviepy #import moviepy
from selenium import webdriver
#from selenium.webdriver.chrome.webdriver import WebDriver
#from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
#twitter #twitter
import tweepy import tweepy
#Thread #Thread
import asyncio #import asyncio
import aiohttp #import aiohttp
from pathlib import Path from pathlib import Path
from sqlalchemy import create_engine #from sqlalchemy import create_engine
from sqlalchemy.ext.declarative import declarative_base from sqlalchemy.ext.declarative import declarative_base
import sqlalchemy import sqlalchemy
from sqlalchemy import null from sqlalchemy import null
@@ -631,22 +630,20 @@ def write_to_database(data, outputs):
sqlalchemy.null() sqlalchemy.null()
cols = ["name", "comment", 'rating','picsURL','picsLocalpath','source','date','address', cols = ["name", "comment", 'rating','picsURL','picsLocalpath','source','date','address',
'dictPostComplete'] 'dictPostComplete']
cols2 = ["num","name", "comment", 'rating','picsURL','picsLocalpath','source','date', # cols2 = ["num","name", "comment", 'rating','picsURL','picsLocalpath','source','date',
'address','dictPostComplete'] # 'address','dictPostComplete']
df = pd.DataFrame(data, columns=cols) df = pd.DataFrame(data, columns=cols)
df2 = pd.DataFrame(outputs['xlsdf'].values, columns=cols2) # df2 = pd.DataFrame(outputs['xlsdf'].values, columns=cols2)
#df2 = df1.where((pd.notnull(df)), None) # take out NAN problems # print ('Dropped items not included in sync to database: ',df2.dropna(inplace=True))
#df3.astype(object).where(pd.notnull(df2), None)
print ('Dropped items not included in sync to database: ',df2.dropna(inplace=True))
rows = list(data) rows = list(data)
if env.needreversed: if env.needreversed:
rows = reversed(rows) rows = reversed(rows)
#jsonposts = json.dumps(outputs['posts'], default=Posts) #jsonposts = json.dumps(outputs['posts'], default=Posts)
print("Encode Object into JSON formatted Data using jsonpickle") print("Encode Object into JSON formatted Data using jsonpickle")
jsonposts = jsonpickle.encode(outputs['posts'], unpicklable=False) jsonposts = jsonpickle.encode(outputs['posts'], unpicklable=False)
for processrow in df2.values: for processrow in outputs['postssession']:
if (processrow[1] in df.values): if (processrow[1] in df.values):
print (' Row ',processrow[0],' ', processrow[1],' already in XLS sheet') print (' Row ',processrow[0],' ', processrow[1],' already in database')
d2_row = Posts(name=processrow[1],comment=processrow[2],rating=processrow[3], d2_row = Posts(name=processrow[1],comment=processrow[2],rating=processrow[3],
picsURL=processrow[4],picsLocalpath=processrow[5],source=processrow[6], picsURL=processrow[4],picsLocalpath=processrow[5],source=processrow[6],
date=processrow[7],address=processrow[8],dictPostComplete=processrow[9]) date=processrow[7],address=processrow[8],dictPostComplete=processrow[9])
@@ -751,6 +748,16 @@ def get_wordpress_post_id_and_link(postname,headers2):
################################################################################################## ##################################################################################################
def check_wordpress_post(postname,postdate,headers2): def check_wordpress_post(postname,postdate,headers2):
""" Checks workpress website to see if a post already exists
Args:
postname (_type_): _description_
postdate (_type_): _description_
headers2 (_type_): _description_
Returns:
_type_: _description_
"""
response = requests.get(env.wpAPI+"/posts?search="+postname, headers=headers2,timeout=40) response = requests.get(env.wpAPI+"/posts?search="+postname, headers=headers2,timeout=40)
result = response.json() result = response.json()
if len(result) > 0 : if len(result) > 0 :
@@ -770,6 +777,14 @@ def check_wordpress_post(postname,postdate,headers2):
# Function to get the featured photo ID of a WordPress post # Function to get the featured photo ID of a WordPress post
def get_wordpress_featured_photo_id(post_id): def get_wordpress_featured_photo_id(post_id):
""" Get photoid from featured photo
Args:
post_id (_type_): _description_
Returns:
_type_: _description_
"""
# Make a GET request to the WordPress REST API to retrieve media details # Make a GET request to the WordPress REST API to retrieve media details
response = requests.get(f"{env.wpAPI}?parent={post_id}",timeout=50) response = requests.get(f"{env.wpAPI}?parent={post_id}",timeout=50)
# Check if the request was successful # Check if the request was successful