def test_api():
class MySettings(Settings):
web = {"with_ajax": False}
api = Api('https://news.ycombinator.com/', settings=MySettings)
class Post(Item):
url = XPath('//a[@class="storylink"][1]/@href')
title = XPath('//a[@class="storylink"][1]/text()')
class Meta:
source = XPath('//tr[@class="athing"]')
route = {'/all?page=:page': '/news?p=:page'}
class Page(Item):
next_page = XPath('//a[@class="morelink"]/@href')
class Meta:
source = None
route = {'/all?page=:page': '/news?p=:page'}
def clean_next_page(self, next_page):
return "http://127.0.0.1:5000/" + str(next_page)
api.register(Post)
api.register(Page)
api.parse('/news?p=1')
def test_api_with_ajax():
from toapi import XPath, Item, Api
api = Api('https://news.ycombinator.com/', with_ajax=True)
class Post(Item):
url = XPath('//a[@class="storylink"][1]/@href')
title = XPath('//a[@class="storylink"][1]/text()')
class Meta:
source = XPath('//tr[@class="athing"]')
route = '/news\?p=\d+'
class Page(Item):
next_page = XPath('//a[@class="morelink"]/@href')
class Meta:
source = None
route = '/news\?p=\d+'
def clean_next_page(self, next_page):
return "http://127.0.0.1:5000/" + next_page
api.register(Post)
api.register(Page)
print(api.parse('/news?p=1'))
def test_api_with_ajax():
from toapi import XPath, Item, Api
api = Api('https://news.ycombinator.com/', with_ajax=True)
class Post(Item):
url = XPath('//a[@class="storylink"][1]/@href')
title = XPath('//a[@class="storylink"][1]/text()')
class Meta:
source = XPath('//tr[@class="athing"]')
route = '/news\?p=\d+'
class Page(Item):
next_page = XPath('//a[@class="morelink"]/@href')
class Meta:
source = None
route = '/news\?p=\d+'
api.parse('/news?p=1')
def test_api_with_ajax():
from toapi import XPath, Item, Api
api = Api('https://news.ycombinator.com/', with_ajax=True)
class Post(Item):
url = XPath('//a[@class="storylink"][1]/@href')
title = XPath('//a[@class="storylink"][1]/text()')
class Meta:
source = XPath('//tr[@class="athing"]')
route = '/'
api.register(Post)
print(api.parse('/'))
else:
return ''.join(
[i.text.strip().replace(u'\xa0', '') for i in title])
def clean_url(self, value):
return value
api.register(Post)
if __name__ == '__main__':
headers = {
'User-Agent':
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)"
}
print(api.parse('/250/?start=25', headers=headers))
api.serve()
# Visit http://127.0.0.1:5000/250/
# http://127.0.0.1:5000/250/?start=25
# http://127.0.0.1:5000/250/?start=50
# ...
"""
{
"post": [
{
"title": "肖申克的救赎/The Shawshank Redemption",
"url": "https://movie.douban.com/subject/1292052/"
},
{
"title": "霸王别姬",
"url": "https://movie.douban.com/subject/1291546/"
def clean_title(self, title):
if isinstance(title, unicode):
return title.replace(u'\xa0', '')
else:
return ''.join(
[i.text.strip().replace(u'\xa0', '') for i in title])
api.register(Post)
if __name__ == '__main__':
headers = {
'User-Agent':
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)"
}
pprint(api.parse('/', headers=headers))
api.serve()
# Visit http://127.0.0.1:5000/
# http://127.0.0.1:5000/?start=25
# http://127.0.0.1:5000/?start=50
# ...
"""
{
"post": [
{
"title": "肖申克的救赎/The Shawshank Redemption",
"url": "https://movie.douban.com/subject/1292052/"
},
{
"title": "霸王别姬",
"url": "https://movie.douban.com/subject/1291546/"
for node in title[0].itertext():
text += node
title = text.strip()
return title
class Meta:
source = Css('li.b_algo')
route = {'/:wd': '/search?q=:wd&ensearch=1'}
class Baidu(Bing):
__name__ = 'baidu'
__base_url__ = 'http://www.baidu.com'
url = Css('h3.t a', attr='href')
title = Css('h3.t a')
class Meta:
source = Css('div.result')
route = {'/:wd': '/s?wd=:wd&ie=utf-8&vf_bl=1'}
api.register(Baidu)
api.register(Bing)
if __name__ == '__main__':
print(api.parse('/python'))
api.serve()
# Visit http://127.0.0.1:5000/python
route = '/'
def clean_title(self, title):
if isinstance(title, unicode):
return title.replace(u'\xa0', '')
else:
return ''.join([i.text.strip().replace(u'\xa0', '') for i in title])
api.register(Post)
if __name__ == '__main__':
headers = {
'User-Agent': "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)"
}
api.parse('/', headers=headers)
api.serve()
# Visit http://127.0.0.1:5000/
# http://127.0.0.1:5000/?start=25
# http://127.0.0.1:5000/?start=50
# ...
"""
{
"post": [
{
"title": "肖申克的救赎/The Shawshank Redemption",
"url": "https://movie.douban.com/subject/1292052/"
},
{
"title": "霸王别姬",