Answers for "data scraper python"

web scraper python

from requests import get
from requests.exceptions import RequestException
from contextlib import closing
from bs4 import BeautifulSoup

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'

web scraper python

>>> raw_html = simple_get('http://www.fabpedigree.com/james/mathmen.htm')
>>> html = BeautifulSoup(raw_html, 'html.parser')
>>> for i, li in enumerate(html.select('li')):
        print(i, li.text)

0  Isaac Newton
 Archimedes
 Carl F. Gauss
 Leonhard Euler
 Bernhard Riemann

1  Archimedes
 Carl F. Gauss
 Leonhard Euler
 Bernhard Riemann

2  Carl F. Gauss
 Leonhard Euler 
 Bernhard Riemann

 3  Leonhard Euler
 Bernhard Riemann

4  Bernhard Riemann

# 5 ... and many more...

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 an exception if we failed to get any data from the url
    raise Exception('Error retrieving contents at {}'.format(url))

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 is a template string that is used to build a URL.
    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:
            # Strip commas
            link_text = hit_link[0].text.replace(',', '')
            try:
                # Convert to integer
                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

web scraper python

def simple_get(url):
    """
    Attempts to get the content at `url` by making an HTTP GET request.
    If the content-type of response is some kind of HTML/XML, return the
    text content, otherwise return None.
    """
    try:
        with closing(get(url, stream=True)) as resp:
            if is_good_response(resp):
                return resp.content
            else:
                return None

    except RequestException as e:
        log_error('Error during requests to {0} : {1}'.format(url, str(e)))
        return None


def is_good_response(resp):
    """
    Returns True if the response seems to be HTML, False otherwise.
    """
    content_type = resp.headers['Content-Type'].lower()
    return (resp.status_code == 200 
            and content_type is not None 
            and content_type.find('html') > -1)


def log_error(e):
    """
    It is always a good idea to log errors. 
    This function just prints them, but you can
    make it do anything.
    """
    print(e)