import codecs from bs4 import BeautifulSoup # Reading the data inside the xml file to a variable under the name data with codecs.open('c:/tmp/sitemap.xml', 'r','utf-8') as f: data = f.read() # Passing the stored data inside the beautifulsoup parser bs_data = BeautifulSoup(data, 'xml') # Finding all instances of tag b_unique = bs_data.find_all('url') cnt=0 for el in b_unique: loc=el.find('loc') print(loc.text) #b_name = bs_data.find('child', {'name':'Acer'}) #print(b_unique) # Using find() to extract attributes of the first instance of the tag #b_name = bs_data.find('child', {'name':'Acer'}) #print(b_name) # Extracting the data stored in a specific attribute of the `child` tag #value = b_name.get('qty') #print(value)
