various snippents

comments

# extract lines with c-style comments
sed -ne '/\/\*/ bp; /\/\// p; b; :p; p; /\*\// b; n; bp;'

radiolab.py

# -*- coding: utf-8 -*-
import scrapy
import urllib.request
import os

def remove_prefix(text, prefix):
    if text.startswith(prefix):
        return text[len(prefix):]
    return text

class RarchiveSpider(scrapy.Spider):
    name = 'rarchive'
    allowed_domains = ['www.radiolab.org']
    start_urls = ['http://www.radiolab.org/archive/']

    def parse(self, response):
        for story in response.xpath('//div[@id="radiolab-archive"]//a[contains(@href, "/story/")]/@href').extract():
            yield scrapy.Request(story, callback=self.parse_story)
        pass

    def parse_story(self, response):
        player = response.css('div.inline_audioplayer_wrapper').xpath('div[@data-width="620"]')
        title = player.xpath('@data-title').extract()[0]
        mp3url = player.xpath('@data-download').extract()[0]
        se = response.xpath('//div[@class="seanum-epnum"]/text()').extract()
        #podtrac = 'https://www.podtrac.com/pts/redirect.mp3/'
        if not se:
            se = ["season 0 | ep 0"]
        s = se[0].split(' ')[1]
        e = se[0].split(' ')[4]
        filename = 'episodes/s{}e{} {}.mp3'.format(s, e, title)
        if not os.path.isfile(filename):
            urllib.request.urlretrieve(mp3url, filename)
        yield {
            'title': title,
            'mp3': mp3url,
            'season': s,
            'episode' : e
        }