def test_api():
api = Api()
@api.site('https://news.ycombinator.com')
@api.list('.athing')
@api.route('/posts?page={page}', '/news?p={page}')
@api.route('/posts', '/news?p=1')
class Post(Item):
url = Attr('.storylink', 'href')
title = Text('.storylink')
@api.site('https://news.ycombinator.com')
@api.route('/posts?page={page}', '/news?p={page}')
@api.route('/posts', '/news?p=1')
class Page(Item):
next_page = Attr('.morelink', 'href')
def clean_next_page(self, value):
return api.convert_string('/' + value, '/news?p={page}', request.host_url.strip('/') + '/posts?page={page}')
app = App(api.app)
with pytest.raises(SystemExit):
api.run(port=-1)
app.get('/posts?page=1')
app.get('/posts?page=1')
print(cli.__dict__)
def test_api():
api = Api()
@api.site("https://news.ycombinator.com")
@api.list(".athing")
@api.route("/posts?page={page}", "/news?p={page}")
@api.route("/posts", "/news?p=1")
class Post(Item):
url = Attr(".storylink", "href")
title = Text(".storylink")
@api.site("https://news.ycombinator.com")
@api.route("/posts?page={page}", "/news?p={page}")
@api.route("/posts", "/news?p=1")
class Page(Item):
next_page = Attr(".morelink", "href")
def clean_next_page(self, value):
return api.convert_string(
"/" + value,
"/news?p={page}",
request.host_url.strip("/") + "/posts?page={page}",
)
app = App(api.app)
with pytest.raises(SystemExit):
api.run(port=-1)
app.get("/posts?page=1")
app.get("/posts?page=1")
print(cli.__dict__)
from htmlparsing import Attr, Text
from toapi import Api, Item
api = Api()
@api.site('https://minwook-shin.github.io')
@api.list('.post')
@api.route('/api', '/')
class Post(Item):
url = Attr('.read-more', 'href')
title = Text('h1 > a')
api.run(debug=True, host='0.0.0.0', port=5000)
from toapi import Api, Item
api = Api(browser="/home/bug/桌面/geckodriver")
@api.site("https://news.ycombinator.com")
@api.list(".athing")
@api.route("/posts?page={page}", "/news?p={page}")
@api.route("/posts", "/news?p=1")
class Post(Item):
url = Attr(".storylink", "href")
title = Text(".storylink")
@api.site("https://news.ycombinator.com")
@api.route("/posts?page={page}", "/news?p={page}")
@api.route("/posts", "/news?p=1")
class Page(Item):
next_page = Attr(".morelink", "href")
def clean_next_page(self, value):
return api.convert_string(
"/" + value,
"/news?p={page}",
request.host_url.strip("/") + "/posts?page={page}",
)
api.run(debug=True, host="0.0.0.0", port=5000)
# encoding:utf-8
'''
Toapi 是一个能够将任何 web 网站转化为 api 服务的库。
这是一个让所有网站都提供API的Python库。以前，我们爬取数据，然后把数据存起来，再创造一个api服务以便其他人可以访问。为此，我们还要定期更新我们的数据。
这个库让这一切变得容易起来。你要做的就是定义好你的数据，然后这些数据就会自动地变成可以访问的API。
'''
from flask import request
from htmlparsing import Attr, Text
from toapi import Api, Item
api = Api()
@api.site('http://www.itest.info')
@api.list('.col-md-3')
@api.route('/courses?page={page}', '/courses')
@api.route('/courses', '/courses')
class Course(Item):
url = Attr('a', 'href')
title = Text('h4')
api.run(debug=True, host='0.0.0.0', port=12306)
img = Attr('a.cook-img', 'style')
url = Attr('a.cook-img', 'href')
title = Text('div.cook-info > a.cookname')
major = Text('div.cook-info > p.major')
def clean_img(self, img):
re_img = re.compile(
'background: url[(](.*)[)] no-repeat center center;background-size: cover;position: relative;'
)
return re_img.match(img).groups()[0]
@api.site('https://www.douguo.com')
@api.route('/search/{keyword}/{page}', '/search/recipe/{keyword}/0/{page}')
@api.route('/search/{keyword}', '/search/recipe/{keyword}')
class Page(Item):
current = Attr('div.mt20 > div.pages > a.anext', 'href')
total = Attr('div.mt20 > div.pages > a.alast', 'href')
def clean_total(self, total):
return int(total.rsplit('/', 1)[1])
def clean_current(self, current):
print(current)
return int(current.rsplit('/', 1)[1]) - 20
if __name__ == '__main__':
api.run('0.0.0.0', debug=True)