def crawl(self, pub_date):
feed = self.parse_feed('http://www.smbc-comics.com/rss.php')
for entry in feed.for_date(pub_date):
title = entry.title.replace(
'Saturday Morning Breakfast Cereal - ', '')
url_1 = entry.summary.src('img[src*="/comics/"]')
page = self.parse_page(entry.link)
url_2 = page.src('#aftercomic img')
return [CrawlerImage(url_1, title), CrawlerImage(url_2)]
def crawl(self, pub_date):
feed = self.parse_feed('http://www.darklegacycomics.com/feed.xml')
for entry in feed.for_date(pub_date):
title = entry.title
page = self.parse_page(entry.link)
url = page.src('img.comic-image')
return CrawlerImage(url, title)
def crawl(self, pub_date):
page = self.parse_page('http://www.redmeat.com/max-cannon/FreshMeat')
url = page.src('.comicStrip img')
title = page.alt('.comicStrip img')
if pub_date.strftime('%Y-%m-%d') not in url:
return
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed(
'http://www.phdcomics.com/gradfeed.php')
for entry in feed.for_date(pub_date):
url = entry.summary.src('img')
title = entry.title.split("'")[1]
return CrawlerImage(url, title)
def crawl(self, pub_date):
page_url = 'http://www.gunshowcomic.com/d/%s.html' % (
pub_date.strftime('%Y%m%d'), )
page = self.parse_page(page_url)
urls = page.src('img[src^="http://gunshowcomic.com/comics/"]',
allow_multiple=True)
return [CrawlerImage(url) for url in urls]
def crawl(self, pub_date):
feed = self.parse_feed(
'http://basicinstructions.net/basic-instructions/rss.xml')
for entry in feed.for_date(pub_date):
url = entry.summary.src('img[src*="/storage/"][src*=".gif"]')
title = entry.title
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed(
'http://www.creators.com/comics/liberty-meadows.rss')
for entry in feed.for_date(pub_date):
page = self.parse_page(entry.link)
url = page.src('img[src*="_thumb"]').replace('thumb', 'image')
return CrawlerImage(url)
def crawl(self, pub_date):
feed = self.parse_feed('http://cdn.sheldoncomics.com/rss.xml')
for entry in feed.for_date(pub_date):
if 'Comic' not in entry.tags:
continue
url = entry.content0.src('img[src*="/strips/"]')
return CrawlerImage(url)
def crawl(self, pub_date):
page_url = 'http://penny-arcade.com/comic/%s' % (
pub_date.strftime('%Y/%m/%d'), )
page = self.parse_page(page_url)
title = page.alt('#comicFrame img')
url = page.src('#comicFrame img')
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://abstrusegoose.com/atomfeed.xml')
for entry in feed.for_date(pub_date):
url = entry.summary.src('img[src*="/strips/"]')
title = entry.title
text = entry.summary.title('img[src*="/strips/"]')
return CrawlerImage(url, title, text)
def crawl(self, pub_date):
page_url = 'http://kindofnormal.com/wumo/%s' % (
pub_date.strftime('%Y/%m/%d'))
page = self.parse_page(page_url)
url = page.href('link[rel="image_src"]')
title = page.alt('img[src="%s"]' % url)
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://darthsanddroids.net/rss.xml')
for entry in feed.for_date(pub_date):
if entry.title.startswith('Episode'):
url = entry.summary.src('img')
title = entry.title
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://www.goominet.com/unspeakable-vault/'
'?type=103&ecorss[clear_cache]=1')
for entry in feed.for_date(pub_date):
url = entry.summary.src('img[src*="/tx_cenostripviewer/"]')
title = entry.title
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://sssscomic.com/ssss-feed.xml')
for entry in feed.all():
page = self.parse_page(entry.link)
url = page.src('img.comicnormal')
title = entry.title.replace('SSSS page', 'Page')
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://axecop.com/feed/')
for entry in feed.for_date(pub_date):
title = entry.title
url = entry.summary.src('img[src*="/wp-content/uploads/"]')
url = url.replace('-150x150', '')
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://www.rsspect.com/rss/qwantz.xml')
for entry in feed.for_date(pub_date):
url = entry.summary.src('img[src*="/comics/"]')
title = entry.title
text = entry.summary.title('img[src*="/comics/"]')
return CrawlerImage(url, title, text)
def crawl(self, pub_date):
feed = self.parse_feed(
'http://www.myextralife.com/category/comic/feed/')
for entry in feed.for_date(pub_date):
url = entry.content0.src('img[src*="/wp-content/"]')
title = entry.title
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://www.blasternation.com/rss.php')
for entry in feed.for_date(pub_date):
page = self.parse_page(entry.link)
url = page.src('img#cc-comic')
title = entry.title.replace('Blaster Nation - ', '')
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://thisishistorictimes.com/feed/')
for entry in feed.for_date(pub_date):
page = self.parse_page(entry.link)
url = page.src('img[src*="/wp-content/uploads/"]')
title = entry.title
return CrawlerImage(url, title)
def crawl(self, pub_date):
page_url = 'http://www.crfh.net/d2/%s.html' % (
pub_date.strftime('%Y%m%d'), )
page = self.parse_page(page_url)
url = page.src('img[src*="crfh%s"]' % pub_date.strftime('%Y%m%d'))
url = url.replace('\n', '')
return CrawlerImage(url)
def crawl(self, pub_date):
feed = self.parse_feed('http://www.goblinscomic.com/feed/')
for entry in feed.for_date(pub_date):
if 'Comics' not in entry.tags:
continue
url = entry.summary.src('img[src*="/comics/"]')
return CrawlerImage(url)
def crawl(self, pub_date):
feed = self.parse_feed(
'http://www.donthitsave.com/donthitsavefeed.xml')
for entry in feed.for_date(pub_date):
url = entry.summary.src('img')
title = entry.title
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed(
'http://www.little-gamers.com/category/comic/feed')
for entry in feed.for_date(pub_date):
url = entry.summary.src('img')
title = entry.title
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://www.tehgladiators.com/rss.xml')
for entry in feed.for_date(pub_date):
page = self.parse_page(entry.link)
url = page.src('img[alt^="Teh Gladiators Webcomic"]')
title = entry.title
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://feeds.feedburner.com/satwcomic')
for entry in feed.all():
page = self.parse_page(entry.link)
url = page.src('img[itemprop="image"]')
title = entry.title
text = page.text('span[itemprop="articleBody"]').strip()
return CrawlerImage(url, title, text)
def crawl(self, pub_date):
feed = self.parse_feed('http://www.megatokyo.com/rss/megatokyo.xml')
for entry in feed.for_date(pub_date):
if entry.title.startswith('Comic ['):
title = entry.title.split('"')[1]
page = self.parse_page(entry.link)
url = page.src('img[src*="/strips/"]')
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://www.savagechickens.com/feed')
for entry in feed.for_date(pub_date):
if 'Cartoons' not in entry.tags:
print 'skipping'
url = entry.content0.src('img[src*="/wp-content/"]')
title = entry.title
return CrawlerImage(url, title)
def crawl(self, pub_date):
feed = self.parse_feed('http://www.exocomics.com/feed')
for entry in feed.for_date(pub_date):
title = entry.title
page = self.parse_page(entry.link)
url = page.src('.comic img')
text = page.title('.comic img')
return CrawlerImage(url, title, text)
def crawl(self, pub_date):
if pub_date.weekday() == 6:
url = 'http://picayune.uclick.com/comics/ga/%s.jpg' % (
pub_date.strftime('%Y/ga%y%m%d'), )
else:
url = 'http://images.ucomics.com/comics/ga/%s.gif' % (
pub_date.strftime('%Y/ga%y%m%d'), )
return CrawlerImage(url)
def crawl(self, pub_date):
feed = self.parse_feed('http://thepunchlineismachismo.com/feed')
for entry in feed.for_date(pub_date):
url = entry.summary.src('img[src*="/wp-content/uploads/"]')
if url is not None:
url = url.replace('-150x150', '')
title = entry.title
return CrawlerImage(url, title)
