def main(roster_row):
try:
logger = get_logger(roster_row) # Get a standard logger
##########
# Begin core specific scraping code
if roster_row['State'].lower(
) != THIS_STATE or roster_row['County'].lower() != THIS_COUNTY:
raise Exception(
"Expected county definition info from _%s, %s_, but found info: _%s_"
% (THIS_COUNTY, THIS_STATE, roster_row))
crawlers.save_single_page(
roster_row,
filetype='html') # try to call a known crawler if possible
# End core specific scraping code
##########
#Close the browser
logger.info('complete!')
except Exception as errorMessage:
try:
browser.close()
record_error(message=str(errorMessage),
roster_row=roster_row,
browser=browser)
except:
record_error(message=str(errorMessage), roster_row=roster_row)
# Record error in S3 for a general error
logger.error('Error: %s', errorMessage)
# Log error
sys.exit(1)
def main(roster_row):
try:
logger = get_logger(roster_row) # Get a standard logger
# Here are standard variable values/how to initialize them.
# These aren't initialized here since in the save_single_page
# case, they can be done in the called function
#browser = get_browser() # Get a standard browser
#urlAddress = roster_row['Working Link'] # Set the main URL from the spreadsheet
#page_index = 0 # Set an initial value of "page_index", which we will use to separate output pages
#logger.info('Set working link to _%s_', urlAddress) # Log the chosen URL
##########
# Begin core specific scraping code
if roster_row['State'].lower() != THIS_STATE or roster_row['County'].lower() != THIS_COUNTY:
raise Exception("Expected county definition info from _%s, %s_, but found info: _%s_" % (THIS_COUNTY, THIS_STATE, roster_row))
crawlers.save_single_page(roster_row) # try to call a known crawler if possible
## Code to save a page and log appropriately
#save_to_s3(store_source, page_index, roster_row)
#logger.info('Saved page _%s_', page_index)
# End core specific scraping code
##########
#Close the browser
logger.info('complete!')
except Exception as errorMessage:
browser.close()
record_error(message=str(errorMessage), roster_row=roster_row, browser=browser)
# Record error in S3 for a general error
logger.error('Error: %s', errorMessage)
# Log error
sys.exit(1)
def main(roster_row):
try:
logger = get_logger(roster_row) # Get a standard logger
# Here are standard variable values/how to initialize them.
# These aren't initialized here since in the save_single_page
# case, they can be done in the called function
browser = get_browser() # Get a standard browser
urlAddress = roster_row[
'Working Link'] # Set the main URL from the spreadsheet
page_index = 0 # Set an initial value of "page_index", which we will use to separate output pages
logger.info('Set working link to _%s_',
urlAddress) # Log the chosen URL
##########
# Begin core specific scraping code
if roster_row['State'].lower(
) != THIS_STATE or roster_row['County'].lower() != THIS_COUNTY:
raise Exception(
"Expected county definition info from _%s, %s_, but found info: _%s_"
% (THIS_COUNTY, THIS_STATE, roster_row))
crawlers.save_single_page(
roster_row) # try to call a known crawler if possible
browser.get(urlAddress)
#Show all inmates instead of 6 per page
time.sleep(np.random.uniform(5, 10, 1))
show_all = browser.find_element_by_xpath('//*[@id="inmatesPerPage"]')
show_all.send_keys('All')
logger.info('clicked "All"')
#Wait
time.sleep(np.random.uniform(15, 20, 1))
#Extract the HTML
store_source = browser.page_source
## Code to save a page and log appropriately
save_to_s3(store_source, page_index, roster_row)
logger.info('Saved page _%s_', page_index)
# End core specific scraping code
##########
#Close the browser
logger.info('complete!')
except Exception as errorMessage:
try:
browser.close()
record_error(message=str(errorMessage),
roster_row=roster_row,
browser=browser)
except:
record_error(message=str(errorMessage), roster_row=roster_row)
# Record error in S3 for a general error
logger.error('Error: %s', errorMessage)
# Log error
sys.exit(1)
