dmoonfire/dosage
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Activity

created Wordpress Scraper class

Browse source
This commit is contained in:
Damjan Košir 2015-08-11 21:31:45 +12:00
parent 0a5b792c32
commit 11f0aa3989
1 changed files with 17 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
dosagelib/plugins/wordpress.py
View file

@ -3,18 +3,21 @@ from dosagelib.helpers import indirectStarter
from ..scraper import make_scraper, _ParserScraper from ..scraper import make_scraper, _ParserScraper
class _WordpressScraper(_ParserScraper):
imageSearch = ('//div[@id="comic"]//img',
'//div[@class="webcomic-image"]//img')
prevSearch = ("//a[contains(concat(' ', text(), ' '), ' Prev ')]",
"//a[contains(concat(' ', text(), ' '), ' Previous ')]",
"//a[contains(concat(' ', @class, ' '), ' navi-prev ')]",
"//a[contains(concat(' ', @class, ' '), ' navi-prev-in ')]",
"//a[contains(concat(' ', @class, ' '), ' navi-previous ')]",
"//a[contains(concat(' ', @class, ' '), ' previous-webcomic-link ')]")
def add(name, url, firstUrl=None, starter=None, textSearch=None, lang=None): def add(name, url, firstUrl=None, starter=None, textSearch=None, lang=None):
attrs = dict( attrs = dict(
name=name, name=name,
url=url, url=url
imageSearch=['//div[@id="comic"]//img',
'//div[@class="webcomic-image"]//img'],
prevSearch=["//a[contains(concat(' ', text(), ' '), ' Prev ')]",
"//a[contains(concat(' ', text(), ' '), ' Previous ')]",
"//a[contains(concat(' ', @class, ' '), ' navi-prev ')]",
"//a[contains(concat(' ', @class, ' '), ' navi-prev-in ')]",
"//a[contains(concat(' ', @class, ' '), ' navi-previous ')]",
"//a[contains(concat(' ', @class, ' '), ' previous-webcomic-link ')]"]
) )
if lang: if lang:
attrs['lang'] = lang attrs['lang'] = lang
@ -24,13 +27,16 @@ def add(name, url, firstUrl=None, starter=None, textSearch=None, lang=None):
attrs['starter'] = starter attrs['starter'] = starter
if textSearch: if textSearch:
attrs['textSearch'] = textSearch attrs['textSearch'] = textSearch
globals()[name] = make_scraper(name, _ParserScraper, **attrs) globals()[name] = make_scraper(name, _WordpressScraper, **attrs)
class Amya(_WordpressScraper):
url = 'http://www.amyachronicles.com/'
add('1997', 'http://1977thecomic.com/') add('1997', 'http://1977thecomic.com/')
add('Alice', 'http://www.alicecomics.com/', add('Alice', 'http://www.alicecomics.com/',
starter=indirectStarter('http://www.alicecomics.com/', '//a[text()="Latest Alice!"]')) starter=indirectStarter('http://www.alicecomics.com/', '//a[text()="Latest Alice!"]'))
add('Amya', 'http://www.amyachronicles.com/')
add('AxeCop', 'http://axecop.com/comic/season-two/') add('AxeCop', 'http://axecop.com/comic/season-two/')
add('Bardsworth', 'http://www.bardsworth.com/') add('Bardsworth', 'http://www.bardsworth.com/')
add('BloodBound', 'http://bloodboundcomic.com/', 'comic/06112006/') add('BloodBound', 'http://bloodboundcomic.com/', 'comic/06112006/')