adicionando exemplos e arrumando dirs

Author: jonasht

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "python.pythonPath": "/home/jonas/0programacao-git/python/webScrapingComPython-livro/scrapingEnv/bin/python3.9"
+}

1-capitulo/1-conectando/scrapetest.py …iroWebScraper/1-conectando/scrapetest.py1-capitulo/1-conectando/scrapetest.py renamed to 01-seuPrimeiroWebScraper/1-conectando/scrapetest.py 1-capitulo/1-conectando/scrapetest.py renamed to 01-seuPrimeiroWebScraper/1-conectando/scrapetest.py

@@ -1,8 +1,6 @@
 from urllib.request import urlopen
-from bs4 import BeautifulSoup
+
 print()
 # no site a um texto em latim, trarah um texto para imprimir
 html = urlopen('http://pythonscraping.com/pages/page1.html')
-bs = BeautifulSoup(html.read(), 'html.parser')
-
-print(bs.h1)
+print(html.read())

01-seuPrimeiroWebScraper/2-executandoBeautifulSoup/scrapetest.py

@@ -0,0 +1,20 @@
+from urllib.request import urlopen
+from bs4 import BeautifulSoup
+print()
+html = urlopen('http://pythonscraping.com/pages/page1.html')
+bs = BeautifulSoup(html.read(), 'html.parser')
+
+print(bs.title)
+# print o titulo da pagina "h1"
+print(bs.h1)
+
+print('div : ')
+print(bs.div)
+
+""" 
+    qualquer uma das funcoes produziriam o mesmo resultado:
+    bs.html.body.h1
+    bs.body.h1
+    bs.html.h1
+"""
+

01-seuPrimeiroWebScraper/3-conectando-seDeFormaConfiavelETratamentoExcecoes/scrapetest.py

@@ -0,0 +1,28 @@
+from urllib.request import urlopen
+from bs4 import BeautifulSoup
+print()
+
+try:
+    
+    html = urlopen('http://pythonscraping.com/pages/page1.html')
+except HTTPError as e:
+    print(e) 
+except URLError as e:
+    print(e)
+    print('the server could not be found')
+    print('o servidor não poode ser encontrado')
+
+else:
+    print('it worked')
+    print('funcionou')
+
+
+    
+    
+bs = BeautifulSoup(html.read(), 'html.parser')
+
+print(bs.title)
+print(bs.h1)
+
+print('div : ')
+print(bs.div)

01-seuPrimeiroWebScraper/3-conectando-seDeFormaConfiavelETratamentoExcecoes/scrapetest2.py

@@ -0,0 +1,28 @@
+from urllib.request import urlopen
+from bs4 import BeautifulSoup
+from urllib.error import HTTPError
+
+        # html = urlopen('http://pythonscraping.com/pages/page1.html')
+def getTitle():
+    
+    print()
+
+    try:
+        html = urlopen(url)
+
+    except HTTPError as e:
+        return None
+    
+    try:
+        bs = BeautifulSoup(html.read(), 'html.parser')
+        title = bs.body.h1
+    except AttributeError as e:
+        return None
+    return title
+
+    title = getTitle('http://www.pythonscraping.com/pages/page1.html')
+    if title == None:
+        print('title could not be found')
+        print('titulo não poode ser encontrado')
+        
+getTitle()