class Cookbook(Item):
title = Text('h2.title')
img = Attr('.recipe-content > div > div > div > a > img', 'src')
browse_count = Text('div.vcnum > span')
collect_count = Text('div.vcnum > span.collectnum')
intro = Text('p.intro')
tip = Text('div.tips > p')
class Repic(Item):
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]
class CourseSeats(Item):
class_num = Text(".classNbrColumnValue > .course-details-link")
total_seats = Text(".availableSeatsColumnValue")
open_seats = total_seats
_tmp_seats = None
def clean_class_num(self, value):
return value.strip()
def clean_total_seats(self, value):
if not self._tmp_seats:
self._tmp_seats = value.split()
return int(self._tmp_seats[2])
def clean_open_seats(self, value):
if not self._tmp_seats:
self._tmp_seats = value.split()
return int(self._tmp_seats[0])
class ClassSeats(Item):
total_seats = Text("#details-side-panel > span")
open_seats = total_seats
_tmp_seats = None
def clean_total_seats(self, value):
if not self._tmp_seats:
self._tmp_seats = value.split()
return int(self._tmp_seats[4])
def clean_open_seats(self, value):
if not self._tmp_seats:
self._tmp_seats = value.split()
return int(self._tmp_seats[2])
class Class(Item):
department = Text("h2")
course = department
title = department
# school = Text(".row > .col-md-7 > span > a")
# instructor = Attr(".nametip", "title")
_tmp_course = None
def clean_department(self, value):
if not self._tmp_course:
self._tmp_course = value.split()
print(f"self._tmp_course = {self._tmp_course}")
return self._tmp_course[0]
def clean_course(self, value):
if not self._tmp_course:
self._tmp_course = value.split()
return self._tmp_course[1]
def clean_title(self, value):
if not self._tmp_course:
self._tmp_course = value.split()
return ' '.join(self._tmp_course[3:])
import requests
from htmlparsing import Element, HTMLParsing, Text, Attr, Parse
url = 'http://localhost:8082/home/serveList.html'
r = requests.get(url)
article_detail = HTMLParsing(r.text).detail({
'title':
Text('a.storylink'),
'points':
Parse('span.score', '>{} points'),
'link':
Attr('a.storylink', 'href')
})
print(article_detail)
class Post(Item):
url = Attr('.read-more', 'href')
title = Text('h1 > a')
class Post(Item):
url = Attr('.storylink', 'no this attribute')
title = Text('.storylink')
class Post(Item):
url = Attr('.storylink', 'href')
title = Text('.storylink')
class Post(Item):
url = Attr(".storylink", "href")
title = Text(".storylink")
class Post(Item):
url = Attr(".storylink", "no this attribute")
title = Text(".storylink")
class Course(Item):
url = Attr('a', 'href')
title = Text('h4')
class Ingredients(Item):
ingredient = Text('span')
weight = Text('span.right')
class Step(Item):
img = Attr('img', 'src')
step = Text('p')
class Selected(Item):
title = Text('.name')
img = Attr('a > img', 'src')
url = Attr('.name', 'href')
"""<Result ('Skip to content',) {}>"""
# Get content or html
print(e.xpath('//a')[5].text)
"""PyPI"""
print(e.xpath('//a')[5].html)
"""<a href="https://pypi.python.org/" title="Python Package Index">PyPI</a>"""
print(e.xpath('//a')[5].markdown)
"""[PyPI](https://pypi.python.org/ "Python Package Index")"""
url = 'https://news.ycombinator.com/'
r = requests.get(url)
article_list = HTMLParsing(r.text).list('.athing', {
'title': Text('a.storylink'),
'link': Attr('a.storylink', 'href')
})
print(article_list)
url = 'https://news.ycombinator.com/item?id=16476454'
r = requests.get(url)
article_detail = HTMLParsing(r.text).detail({
'title':
Text('a.storylink'),
'points':
Parse('span.score', '>{} points'),
'link':
Attr('a.storylink', 'href')
})
print(article_detail)