import urllib
html_str = urllib.urlopen("http://static.decontextualize.com/widgets.html").read()

print len(html_str)

from bs4 import BeautifulSoup
# your code here

document = BeautifulSoup(html_str)
len(document.find_all('h3'))

widget_names = []

widget_names = [tag.string for tag in document.find_all('td', attrs={"class": "widgetname"})]

widget_names

widgets = []

html_str = urllib.urlopen("http://static.decontextualize.com/widgets.html").read()

# your code here
document = BeautifulSoup(html_str)
tr_tags = document.find_all("tr", attrs={'class': 'widgetinfo'})
for tr_tag in tr_tags:
    widget_dict = {}
    for class_ in ("partno", "widgetname", "price", "quantity"):
        tag = tr_tag.find("td", attrs={'class': class_})
        widget_dict[class_] = tag.string
    widgets.append(widget_dict) 
# end your code

widgets

widgets = []

html_str = urllib.urlopen("http://static.decontextualize.com/widgets.html").read()

# your code here
document = BeautifulSoup(html_str)
tr_tags = document.find_all("tr", attrs={'class': 'widgetinfo'})
for tr_tag in tr_tags:
    widget_dict = {}
    for class_ops in (("partno", str), ("widgetname", str), ("price", lambda x: float(x[1:])), ("quantity", int)):
        tag = tr_tag.find("td", attrs={'class': class_ops[0]})
        widget_dict[class_ops[0]] = class_ops[1](tag.string)
    widgets.append(widget_dict) 
# end your code

widgets

import pandas as pd
widgets_df = pd.DataFrame(widgets)
widgets_df

widgets_df['quantity'].sum()

widgets_df[widgets_df['price'] > widgets_df['price'].mean()]

example_html = """
<h2>Camembert</h2>
<p>A soft cheese made in the Camembert region of France.</p>

<h2>Cheddar</h2>
<p>A yellow cheese made in the Cheddar region of... France, probably, idk whatevs.</p>
"""

example_doc = BeautifulSoup(example_html)
cheese_dict = {}
for h2_tag in example_doc.find_all('h2'):
    cheese_name = h2_tag.string
    cheese_desc_tag = h2_tag.find_next_sibling('p')
    cheese_dict[cheese_name] = cheese_desc_tag.string

cheese_dict

hallowed_h3_tag = document.find_all('h3')[2]
table_tag = hallowed_h3_tag.find_next_sibling('table')
len(table_tag.find_all('tr'))

category_counts = {}
# your code here

for h3_tag in document.find_all('h3'):
    table_tag = h3_tag.find_next_sibling('table')
    category_counts[h3_tag.string] = len(table_tag.find_all('tr'))

category_counts