## Copy all elements from sheet row read
for elm in row:
record[recordKeys[key]] = elm
key += 1
## Fill in remainder with empty strings
while key < len(recordKeys):
record[recordKeys[key]] = ''
key += 1
return record
if __name__ == '__main__':
# Initialize Google Sheets for Write
get_credentials = smgs.modelInit()
# Get Headers from google sheets
print('KEYS')
contactKeys = getContactKeys()
directoryKeys = getAgencyDirKeys()
print('')
# Get contact and orginization website data and structure with collected headings
print('RECORDS')
contactRecords = [sheetRecord(row, contactKeys) for row in getContacts()]
orgRecords = [sheetRecord(row, directoryKeys) for row in getAgencyDir()]
print('')
# Create Dataframes
cr = pd.DataFrame(contactRecords)
class DirectoryManager(object):
## The goal of this class is to manage the directory in the enviroment not to be one!
## the directory as well as it access and packaging functions will opporate as utility functions, these
## the routines of this class will call those utility functions
get_credentials = smgs.modelInit()
scraperQueue = None
def __init__(self, orgRecords):
self.orgRecords = orgRecords
#self.get_credentials = smgs.modelInit()
#self.browser = webdriver.Chrome(path_to_chromedriver)
def findOrgRecord(self, organization):
for org in self.orgRecords:
if organization == org['Organization']:
return org
def get_organizations(self):
return [x['Organization'] for x in self.orgRecords]
def orgRecordIndex(self, orgRecord):
return self.orgRecords.index(orgRecord)
def linkList(self, orgRecord):
lis = [
orgRecord['Directory link'], orgRecord['Link 2'],
orgRecord['Link 3'], orgRecord['Link 4']
]
return lis[:lis.index('')]
def writeRecordRow(self, row, index):
"""Google Sheets API Code.
"""
try:
timeString = '{} {}'.format(str(row[0][1]), row[0][2])
print(timeString)
DirectoryManager.dir_on_with_time('__recordRow', timeString)
except BaseException as e:
print(e)
credentials = DirectoryManager.get_credentials()
http = credentials.authorize(smgs.httplib2.Http())
discoveryUrl = ('https://sheets.googleapis.com/$discovery/rest?'
'version=v4')
service = smgs.discovery.build('sheets',
'v4',
http=http,
discoveryServiceUrl=discoveryUrl)
spreadsheet_id = '1p1LNyQhNhDBNEOkYQPV9xcNRe60WDlmnuiPp78hxkIs'
value_input_option = 'RAW'
rangeName = 'Org Leadership Websites!F' + str(index + 2)
values = row
body = {'values': values}
result = service.spreadsheets().values().update(
spreadsheetId=spreadsheet_id,
range=rangeName,
valueInputOption=value_input_option,
body=body).execute()
DirectoryManager.dir_off('__recordRow')
return result
def writeRecordNote(self, note, index):
"""Google Sheets API Code.
"""
DirectoryManager.dir_on('__recordNote')
credentials = DirectoryManager.get_credentials()
http = credentials.authorize(smgs.httplib2.Http())
discoveryUrl = ('https://sheets.googleapis.com/$discovery/rest?'
'version=v4')
service = smgs.discovery.build('sheets',
'v4',
http=http,
discoveryServiceUrl=discoveryUrl)
spreadsheet_id = '1p1LNyQhNhDBNEOkYQPV9xcNRe60WDlmnuiPp78hxkIs'
value_input_option = 'RAW'
rangeName = 'Org Leadership Websites!J' + str(index + 2)
values = [[note]]
body = {'values': values}
result = service.spreadsheets().values().update(
spreadsheetId=spreadsheet_id,
range=rangeName,
valueInputOption=value_input_option,
body=body).execute()
DirectoryManager.dir_off('__recordNote')
return result
@classmethod
def set_app_scraper_queue(cls, q):
DirectoryManager.scraperQueue = q
@classmethod
def dir_on(cls, place):
if DirectoryManager.scraperQueue:
DirectoryManager.scraperQueue.put({'__DIRON': place})
@classmethod
def dir_on_with_time(cls, place, timeString):
if DirectoryManager.scraperQueue:
DirectoryManager.scraperQueue.put({
'__DIRON': place,
'time': timeString
})
@classmethod
def dir_off(cls, place):
if DirectoryManager.scraperQueue:
DirectoryManager.scraperQueue.put({'__DIROFF': place})
@classmethod
def change_on(cls, place):
if DirectoryManager.scraperQueue:
DirectoryManager.scraperQueue.put({'__NEWBROWSERON': place})
@classmethod
def change_off(cls, place):
if DirectoryManager.scraperQueue:
DirectoryManager.scraperQueue.put({'__NEWBROWSEROFF': place})
def run(self):
get_credentials_method = smgs.modelInit()
# Get Headers from google sheets
print('KEYS')
self.startupQueue.put({'progress': 1})
self.startupQueue.put({'message': 'KEYS'})
contactKeys = getContactKeys(get_credentials_method)
self.startupQueue.put({'progress': 2})
directoryKeys = getAgencyDirKeys(get_credentials_method)
self.startupQueue.put({'progress': 3})
print('')
# Get contact and orginization website data and structure with collected headings
print('RECORDS')
self.startupQueue.put({'message': 'RECORDS'})
contactRecords = [
sheetRecord(row, contactKeys)
for row in getContacts(get_credentials_method)
]
self.startupQueue.put({'progress': 4})
self.orgRecords = [
sheetRecord(row, directoryKeys)
for row in getAgencyDir(get_credentials_method)
]
self.startupQueue.put({'progress': 5})
print('')
# Create Dataframes
cr = pd.DataFrame(contactRecords)
dr = pd.DataFrame(self.orgRecords)
print('DATAFRAMES READY')
self.startupQueue.put({'message': 'DATAFRAMES READY', 'progress': 6})
## ////////////////// Initialize Contact Checker Classes with Fresh Data \\\\\\\\\\\\\\\\\\\
# Setup Contact Record Output
cc.ContactSheetOutput.set_output(contactKeys)
self.startupQueue.put({'progress': 7})
# For this scrape session Give the Verification Handler class an Orgsession with Organization Records
dm.OrgSession.set_browser_path(
) ## IMPORTANT STEP: The browser path must be set to the current working directory which varies for different machines
cc.VerificationHandler.set_orgRecords(
dm.HeadlessOrgSession(self.orgRecords))
#self.queue.put({'progress': 'Finishd'})
# For this scrape session Give the Verification Handler class the contact record data
cc.VerificationHandler.set_contactRecords(cr)
cc.ScrapeSession.set_app_scraper_queue(self.scraperQueue)
cc.ScrapeSession.set_app_command_queue(self.commandQueue)
print('CONTACT CHECKER READY')
print('SCRAPE SESSION OPEN')
print('')
self.startupQueue.put({
'message': 'SCRAPE SESSION OPEN',
'progress': 'FINNISHED'
})
## ////////////////// Begin Scraper Loop \\\\\\\\\\\\\\\\\\\
self.commandLoop = True
while self.commandLoop:
self.commandLoop = self.listen_for_cmd()
cc.VerificationHandler.close_browser()
print('SCRAPER THREAD FINNISHED')
def start_scraper(self):
get_credentials_method = smgs.modelInit()
# Get Headers from google sheets
print('KEYS')
self.startupQueue.put({'progress': 'START'})
self.startupQueue.put({'message': 'KEYS',
'__waiting': ScraperThread.ContactKeysVal})
contactKeys = getContactKeys(get_credentials_method)
self.startupQueue.put({'progress': 1,
'__ready': ScraperThread.ContactKeysVal,
'__waiting': ScraperThread.DirectoryKeysVal})
directoryKeys = getAgencyDirKeys(get_credentials_method)
self.startupQueue.put({'progress': 2,
'__ready': ScraperThread.DirectoryKeysVal})
print('')
# Get contact and orginization website data and structure with collected headings
print('RECORDS')
self.startupQueue.put({'message': 'RECORDS',
'__waiting': ScraperThread.ContactRecordsVal})
contactRecords = [sheetRecord(row, contactKeys) for row in getContacts(get_credentials_method)]
self.startupQueue.put({'progress': 3,
'__ready': ScraperThread.ContactRecordsVal,
'__waiting': ScraperThread.AgencyDirectoryVal})
self.orgRecords = [sheetRecord(row, directoryKeys) for row in getAgencyDir(get_credentials_method)]
self.startupQueue.put({'progress': 4,
'__ready': ScraperThread.AgencyDirectoryVal})
print('')
# Create Dataframes
self.startupQueue.put({'__waiting': ScraperThread.DataVal})
cr = pd.DataFrame(contactRecords)
dr = pd.DataFrame(self.orgRecords)
print('DATAFRAMES READY')
self.startupQueue.put({'message': 'DATAFRAMES READY',
'progress': 5,
'__ready': ScraperThread.DataVal})
## ////////////////// Initialize Contact Checker Classes with Fresh Data \\\\\\\\\\\\\\\\\\\
# Setup Contact Record Output
self.startupQueue.put({'__waiting': ScraperThread.OutputVal})
cc.ContactSheetOutput.set_output(contactKeys)
self.startupQueue.put({'progress': 6,
'__ready': ScraperThread.OutputVal,
'__waiting': ScraperThread.BrowserDriverVal})
# For this scrape session Give the Verification Handler class an Orgsession with Organization Records
dm.OrgSession.set_browser_path() ## IMPORTANT STEP: The browser path must be set to the current working directory which varies for different machines
cc.VerificationHandler.set_orgRecords(dm.HeadlessOrgSession(self.orgRecords))
self.startupQueue.put({'progress': 7,
'__ready': ScraperThread.BrowserDriverVal,
'__waiting': ScraperThread.ContactCheckerVal})
# For this scrape session Give the Verification Handler class the contact record data
cc.VerificationHandler.set_contactRecords(cr)
cc.ScrapeSession.set_app_scraper_queue(self.scraperQueue)
cc.ContactSheetOutput.set_app_scraper_queue(self.scraperQueue)
cc.ContactCollector.set_app_scraper_queue(self.scraperQueue)
dm.DirectoryManager.set_app_scraper_queue(self.scraperQueue)
dm.OrgQuery.set_app_scraper_queue(self.scraperQueue)
cc.ScrapeSession.set_app_command_queue(self.commandQueue)
## Count Rows and Finnish up
self.startupQueue.put({'rowCounts': {'contact counts': cc.ContactSheetOutput.count_contacts_rows(),
'output counts': cc.ContactSheetOutput.count_scraper_output_rows()}})
print('CONTACT CHECKER READY')
print('SCRAPE SESSION OPEN')
print('')
self.startupQueue.put({'message': 'SCRAPE SESSION OPEN',
'progress': 'FINNISHED',
'__ready': ScraperThread.ContactCheckerVal})
