Find "Who is Hiring" posts

howiswho.py

import os
import bs4
import requests
import re
import time

def get_page(href):
    print "Getting page:" + href
    time.sleep(2)
    if not href:
        return None
    href = os.path.join("https://news.ycombinator.com", href)
    resp = requests.get(href)
    page = bs4.BeautifulSoup(resp.content, 'html.parser')
    page.href = href
    return page

def next_href(page):
    elements = page.select('td .title a[rel="nofollow"]')
    if elements:
        return elements[0].attrs["href"]
    return None

class pagerange:
    def __init__(self, href):
        self.href = href
    
    def __iter__(self):
        return self
    
    def next(self):
        if self.href:
	    next = get_page(self.href)
	    self.href = next_href(next)
	    return next
	raise StopIteration()

pages = [page for page in pagerange("submitted?id=whoishiring")]
tables = [p.select_one(".athing").parent for p in pages]

all_hiring_regex = re.compile("ask hn.*who is hiring", flags=re.IGNORECASE)
all_posts = []

def extract(entry, extract_posts_regex):
    title = entry[0].select("a")[-1].text
    link = entry[0].select("a")[-1].attrs["href"]
    posts = entry[1].select("a")[-1].text.split(" ")[0]
    top_level_comments = -1
    if extract_posts_regex.match(title):
        page = get_page(link)
        top_level_comments = len(page.select('img[width="0"]'))
    return title, link, top_level_comments, posts

for table in tables:
    rows = table.select("tr")
    entries = [rows[i:i+2] for i in xrange(0, len(rows), 3)]
    entries.pop()
    all_posts.extend([extract(e, all_hiring_regex) for e in entries])

all_hiring = [i for i in all_posts if all_hiring_regex.match(i[0])]

results = [[' ' for x in range(len(all_hiring))] for y in range(20)]

maxpoints = 850
height = 60
maxdatelen = 14

results = []
for x in range(len(all_hiring)):
    post = all_hiring[x]
    result = [' ' for i in range(height)]
    date = all_hiring_regex.match(post[0]).group(1)
    print date + " "* (maxdatelen - len(date)),
    points = float(post[2]) / maxpoints * height
    for y in range(int(round(points))):
        result[y] = 'X'
    print ''.join(result)

A bit buggy, but...

                                                X        
                                                XX       
                                                XXX X    
                                                XXX X  X 
                                               XXXXXX  X 
                                               XXXXXX  X 
                                       X   X XXXXXXXX  XX
                             X      X XX   X XXXXXXXX  XX
                             X     XX XX X X XXXXXXXXXXXX
                       X   X X   XXXXXXX XXX XXXXXXXXXXXX
  X       X      X    XX  XX XXX XXXXXXXXXXXXXXXXXXXXXXXX
XXXXX X  XXXXXXXXXXXXXXX  XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXX X XXXXXXXXXXXXXXXX  XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXX X XXXXXXXXXXXXXXXX  XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXX X XXXXXXXXXXXXXXXX  XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX