html scraper python code example
Example 1: web scraper python
>>> from bs4 import BeautifulSoup
>>> raw_html = open('contrived.html').read()
>>> html = BeautifulSoup(raw_html, 'html.parser')
>>> for p in html.select('p'):
... if p['id'] == 'walrus':
... print(p.text)
'I am the walrus'
Example 2: web scraper python
def get_hits_on_name(name):
"""
Accepts a `name` of a mathematician and returns the number
of hits that mathematician's Wikipedia page received in the
last 60 days, as an `int`
"""
url_root = 'URL_REMOVED_SEE_NOTICE_AT_START_OF_ARTICLE'
response = simple_get(url_root.format(name))
if response is not None:
html = BeautifulSoup(response, 'html.parser')
hit_link = [a for a in html.select('a')
if a['href'].find('latest-60') > -1]
if len(hit_link) > 0:
link_text = hit_link[0].text.replace(',', '')
try:
return int(link_text)
except:
log_error("couldn't parse {} as an `int`".format(link_text))
log_error('No pageviews found for {}'.format(name))
return None
Example 3: web scraper python
def get_names():
"""
Downloads the page where the list of mathematicians is found
and returns a list of strings, one per mathematician
"""
url = 'http://www.fabpedigree.com/james/mathmen.htm'
response = simple_get(url)
if response is not None:
html = BeautifulSoup(response, 'html.parser')
names = set()
for li in html.select('li'):
for name in li.text.split('\n'):
if len(name) > 0:
names.add(name.strip())
return list(names)
raise Exception('Error retrieving contents at {}'.format(url))