Merge pull request nicolomantini#32 from krapes/upload_identifier

Resume, Cover letter and Photo support

README.md

@@ -26,8 +26,10 @@ locations:
 - # Location you want to search for
 - # A second location you want to search in 
 
-cover_letter_loctn:
-- # '/home/PATH_TO_FILE' 
+uploads:
+ Resume: # PATH TO Resume 
+ Cover Letter: # PATH TO cover letter
+ Photo: # PATH TO photo
 
 output_filename:
 - # PATH TO OUTPUT FILE (default output.csv)
@@ -37,6 +39,11 @@ blacklist:
 ```
 __NOTE: AFTER EDITING SAVE FILE, DO NOT COMMIT FILE__
 
+### Uploads
+
+There is no limit to the number of files you can list in the uploads section. 
+The program takes the titles from the input boxes and tries to match them with 
+list in the config file.
 
 ## Execute
 

config.yaml

@@ -2,19 +2,23 @@ username:
 password: 
 
 positions:
-- # positions you want to search for
+- Data Scientist
 - # Another position you want to search for
 - # A third position you want to search for
 
 locations:
-- # Location you want to search for
+- Remote
 - # A second location you want to search in 
 
-cover_letter_loctn:
-- # '/home/PATH_TO_FILE' 
+# --------- Optional Parameters -------
+# uploads:
+#  Resume: # PATH TO Resume 
+#  Cover Letter: # PATH TO cover letter
+#  Photo: # PATH TO photo
 
-output_filename:
-- # PATH TO OUTPUT FILE (default output.csv)
 
-blacklist:
-- # Company names you want to ignore
+# output_filename:
+# - # PATH TO OUTPUT FILE (default output.csv)
+
+# blacklist:
+# - # Company names you want to ignore

easyapplybot.py

@@ -26,20 +26,20 @@ class EasyApplyBot:
 	MAX_SEARCH_TIME = 10*60
 
 
-
 	def __init__(self,
 				 username,
 				 password,
-				 cover_letter_loctn=None,
+				 uploads={},
 				 filename='output.csv',
 				 blacklist=[]):
 
 		print("\nWelcome to Easy Apply Bot\n")
 		dirpath = os.getcwd()
 		print("current directory is : " + dirpath)
 
-		self.cover_letter_loctn = cover_letter_loctn
-		self.appliedJobIDs = self.get_appliedIDs(filename) if self.get_appliedIDs(filename) != None else []
+		self.uploads = uploads
+		past_ids = self.get_appliedIDs(filename)
+		self.appliedJobIDs = past_ids if past_ids != None else []
 		self.filename = filename
 		self.options = self.browser_options()
 		self.browser = driver
@@ -49,13 +49,12 @@ def __init__(self,
 
 
 	def get_appliedIDs(self, filename):
-		print(filename)
 		try:
 			df = pd.read_csv(filename,
 							header=None,
 							names=['timestamp', 'jobID', 'job', 'company', 'attempted', 'result'],
 							lineterminator='\n',
-							encoding = 'utf-8')
+							encoding='utf-8')
 
 			df['timestamp'] = pd.to_datetime(df['timestamp'], format="%Y-%m-%d %H:%M:%S.%f")
 			df = df[df['timestamp'] > (datetime.now() - timedelta(days=2))]
@@ -91,13 +90,10 @@ def start_linkedin(self,username,password):
 		except TimeoutException:
 			print("TimeoutException! Username/password field or login button not found")
 
-
 	def fill_data(self):
 		self.browser.set_window_size(0, 0)
 		self.browser.set_window_position(2000, 2000)
 
-		print(self.cover_letter_loctn)
-
 	def start_apply(self, positions, locations):
 		start = time.time()
 		self.fill_data()
@@ -164,7 +160,6 @@ def applications_loop(self, position, location):
 			jobIDs = [x for x in IDs if x not in self.appliedJobIDs]
 			after = len(jobIDs)
 
-
 			if len(jobIDs) == 0 and len(IDs) > 24:
 				jobs_per_page = jobs_per_page + 25
 				count_job = 0
@@ -236,8 +231,7 @@ def re_extract(text, pattern):
 
 
 	def get_job_page(self, jobID):
-		#root = 'www.linkedin.com'
-		#if root not in job:
+
 		job = 'https://www.linkedin.com/jobs/view/'+ str(jobID)
 		self.browser.get(job)
 		self.job_page = self.load_page(sleep=0.5)
@@ -264,7 +258,6 @@ def is_present(button_locator):
 
 		try:
 			time.sleep(random.uniform(1.5, 2.5))
-			#print(f"Navigating... ")
 			next_locater = (By.CSS_SELECTOR,
 							"button[aria-label='Continue to next step']")
 			review_locater = (By.CSS_SELECTOR,
@@ -275,17 +268,28 @@ def is_present(button_locator):
 									"button[aria-label='Submit application']")
 			error_locator = (By.CSS_SELECTOR,
 							"p[data-test-form-element-error-message='true']")
-			cover_letter = (By.CSS_SELECTOR, "input[name='file']")
+			upload_locator = (By.CSS_SELECTOR, "input[name='file']")
+
+
 
 			submitted = False
 			while True:
 
 				# Upload Cover Letter if possible
-				if is_present(cover_letter):
-					input_button = self.browser.find_elements(cover_letter[0],
-															 cover_letter[1])
+				if is_present(upload_locator):
 
-					input_button[0].send_keys(self.cover_letter_loctn)
+					input_buttons = self.browser.find_elements(upload_locator[0],
+															 upload_locator[1])
+					for input_button in input_buttons:
+						parent = input_button.find_element(By.XPATH, "..")
+						sibling = parent.find_element(By.XPATH, "preceding-sibling::*")
+						grandparent = sibling.find_element(By.XPATH, "..")
+						for key in self.uploads.keys():
+							if key in sibling.text or key in grandparent.text:
+								input_button.send_keys(self.uploads[key])
+
+
+					#input_button[0].send_keys(self.cover_letter_loctn)
 					time.sleep(random.uniform(4.5, 6.5))
 
 				# Click Next or submitt button if possible
@@ -367,6 +371,9 @@ def next_jobs_page(self, position, location, jobs_per_page):
 	def finish_apply(self):
 		self.browser.close()
 
+
+
+
 if __name__ == '__main__':
 
 	with open("config.yaml", 'r') as stream:
@@ -382,13 +389,17 @@ def finish_apply(self):
 
 
 	print(parameters)
-	cover_letter_loctn = parameters.get('cover_letter_loctn', [None])[0]
-	output_filename = parameters.get('output_filename', ['output.csv'])[0]
+
+	output_filename = [f for f in parameters.get('output_filename', ['output.csv']) if f != None]
+	output_filename = output_filename[0] if len(output_filename) > 0 else 'output.csv'
 	blacklist = parameters.get('blacklist', [])
+	uploads = parameters.get('uploads', {})
+	for key in uploads.keys():
+		assert uploads[key] != None
 
 	bot = EasyApplyBot(parameters['username'],
 						parameters['password'],
-						cover_letter_loctn=cover_letter_loctn,
+						uploads=uploads,
 						filename=output_filename,
 						blacklist=blacklist
 						)