Updated Stuff

Author: 1day2die

WebScraper/web - Kopie.py

@@ -6,16 +6,16 @@
 import xlsxwriter
 
 
-baseurl = "https://www.brk.de/rotes-kreuz/adressen/kreisverbaende/detail/0"
-workbook = xlsxwriter.Workbook('Example2.xlsx') 
+baseurl = "SETURL"
+workbook = xlsxwriter.Workbook('Example.xlsx') 
 worksheet = workbook.add_worksheet() 
 row = 0
 column = 0
 
 i = 200
 
 urls = []
-
+# NICE FUNCTION SO SEARCH MULTIPLE DOMAINS 
 while i < 300:
 	url = str(baseurl)+str(i)
 
@@ -27,9 +27,9 @@
 	response = requests.get(each)
 	soup = BeautifulSoup(response.text, "html.parser")
 
-	name = soup.findAll('span', {"itemprop" : "name"})
-	telephone = soup.findAll('span', {"itemprop" : "telephone"})
-	email = soup.findAll('span', {"itemprop" : "email"})
+	name = soup.findAll('span', {"itemprop" : "name"})  #SEARCH FOR A HTMLTAG TO SCRAPE
+	telephone = soup.findAll('span', {"itemprop" : "telephone"})  #SEARCH FOR A HTMLTAG TO SCRAPE
+	email = soup.findAll('span', {"itemprop" : "email"})  #SEARCH FOR A HTMLTAG TO SCRAPE
 
 	#all_spans = "NAME: ", name,"\n Telefon: ", telephone ,"\n Email: ", email
 	all_spans = name, telephone, email

WebScraper/web.py

@@ -6,14 +6,14 @@
 import xlsxwriter
 
 
-baseurl = "https://www.dgwz.de/publikationen/ihk"
-workbook = xlsxwriter.Workbook('Example2.xlsx') 
+baseurl = "SET URL"
+workbook = xlsxwriter.Workbook('Example.xlsx') 
 worksheet = workbook.add_worksheet() 
 
 response = requests.get(baseurl)
 soup = BeautifulSoup(response.text, "html.parser")
 
-h1 = soup.findAll('h1')
+h1 = soup.findAll('h1') #SEARCH FOR A HTMLTAG TO SCRAPE
 row = 0
 column = 0
 for each in h1: