TheThinHLine: fetch bigger images and name image files from sequence number.

This commit is contained in:
Bastian Kleineidam 2014-07-03 18:41:25 +02:00
parent 4845a4ccc1
commit f194e430bc
2 changed files with 22 additions and 6 deletions

View file

@ -1,8 +1,8 @@
Dosage 2.15 (released xx.xx.2014) Dosage 2.15 (released xx.xx.2014)
Features: Features:
- comics: Added Whomp. - comics: Added TheThinHLine, Whomp.
Closes: GH bug #64 Closes: GH bug #64, #67
Fixes: Fixes:
- comics: Fixed DungeonsAndDenizens, GirlGenius, GirlsWithSlingshots, - comics: Fixed DungeonsAndDenizens, GirlGenius, GirlsWithSlingshots,

View file

@ -5,7 +5,7 @@
from re import compile, escape, IGNORECASE from re import compile, escape, IGNORECASE
from ..scraper import _BasicScraper from ..scraper import _BasicScraper
from ..helpers import indirectStarter from ..helpers import indirectStarter
from ..util import tagre from ..util import tagre, fetchUrl, getPageContent
class TheBrads(_BasicScraper): class TheBrads(_BasicScraper):
@ -213,13 +213,29 @@ class TheOuterQuarter(_BasicScraper):
class TheThinHLine(_BasicScraper): class TheThinHLine(_BasicScraper):
description = u'the thin H line. Proudly mediocre. NSFW.' description = u'the thin H line. Proudly mediocre. NSFW.'
url = 'http://thinhline.tumblr.com/' url = 'http://thinhline.tumblr.com/'
rurl = escape(url)
stripUrl = url + 'post/%s' stripUrl = url + 'post/%s'
firstStripUrl = stripUrl % '3517345105' firstStripUrl = stripUrl % '3517345105'
imageSearch = compile(tagre('a', 'href', '%simage[^"]+' % url) + tagre('img', 'src', '([^"]+media.tumblr.com/[^"]+)')) imageSearch = compile(tagre('img', 'data-src', r'([^"]+media.tumblr.com/[^"]+)', before='content-image'))
prevSearch = compile(r'<a href="([^"]+)">&gt;</a>') prevSearch = compile(tagre("a", "href", r'([^"]+)') + '&gt;</a>')
starter = indirectStarter(url, compile(r'<a href="([^"]+)" class="timestamp"')) starter = indirectStarter(url, compile(tagre("a", "href", r'([^"]+)', after='class="timestamp"')))
adult = True adult = True
indirectImageSearch = compile(tagre('a', 'href', r'(%simage/\d+)' % rurl))
def getComicStrip(self, url, data, baseUrl):
"""The comic strip image is in a separate page."""
pageUrl = fetchUrl(url, data, baseUrl, self.indirectImageSearch)
pageData, pageBaseUrl = getPageContent(pageUrl, self.session)
return super(TheThinHLine, self).getComicStrip(pageUrl, pageData, pageBaseUrl)
@classmethod
def namer(cls, imageUrl, pageUrl):
"""Remove trailing digit from day number."""
num = pageUrl.split('/')[-1]
ext = imageUrl.rsplit('.', 1)[1]
return "thethinhline-%s.%s" % (num, ext)
class ThreePanelSoul(_BasicScraper): class ThreePanelSoul(_BasicScraper):
url = 'http://threepanelsoul.com/' url = 'http://threepanelsoul.com/'