Last active
August 29, 2015 13:56
-
-
Save dieterplex/9085603 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/python | |
| # -*- coding: utf-8 -*- | |
| import sys | |
| import urllib2 | |
| from HTMLParser import HTMLParser | |
| def write(value=''): | |
| sys.stdout.write(str(value)) | |
| class MyHTMLParser(HTMLParser): | |
| row, col = 0, 0 | |
| def handle_starttag(self, tag, attrs): | |
| if tag == 'table': | |
| write('[') | |
| if self.row: | |
| if tag == 'tr': | |
| if self.row > 1: | |
| write(', ') | |
| write('{') | |
| if tag == 'td': | |
| fm = ['"name": "', '"國語": ', '"數學": ', '"自然": ', '"社會": ', '"健康教育": '] | |
| write(fm[self.col]) | |
| def handle_endtag(self, tag): | |
| if tag == 'table': | |
| write(']') | |
| if self.row: | |
| if tag == 'td': | |
| if self.col == 0: | |
| write('", "grades": {') | |
| elif self.col == 5: | |
| write('}') | |
| else: | |
| write(', ') | |
| self.col = self.col + 1 | |
| if tag == 'tr': | |
| write('}') | |
| self.col = 0 | |
| # skip header | |
| if tag == 'tr': | |
| self.row = self.row + 1 | |
| def handle_data(self, data): | |
| if self.row: | |
| write(data.strip()) | |
| response = urllib2.urlopen('http://axe-level-1.herokuapp.com/') | |
| html = response.read() | |
| parser = MyHTMLParser() | |
| parser.feed(html) | |
| #[{"name": "王小明", "grades": {"國語": 90, "數學": 89, ...}}, ... ] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/python | |
| #-*- coding: utf-8 -*- | |
| import urllib2 | |
| import sys | |
| from HTMLParser import HTMLParser | |
| AXE_URL = 'http://axe-level-1.herokuapp.com/lv2' | |
| def get_page_raw_data(page_num=1): | |
| url ='%s/?page=%s' % (AXE_URL, page_num) | |
| response = urllib2.urlopen(url) | |
| html = response.read() | |
| return html | |
| def write(value=''): | |
| sys.stdout.write(str(value)) | |
| class MyHTMLParser2(HTMLParser): | |
| row, col = 0, 0 | |
| fm = ['"town": "', '"village": "', '"name" : "'] | |
| def handle_starttag(self, tag, attrs): | |
| if self.row: | |
| if tag == 'tr': | |
| if self.row > 1: | |
| write(', ') | |
| write('{') | |
| if tag == 'td': | |
| write(self.fm[self.col]) | |
| def handle_endtag(self, tag): | |
| if tag == 'table': | |
| self.row = 0 | |
| if self.row: | |
| if tag == 'td': | |
| if self.col == 2: | |
| write('"') | |
| else: | |
| write('", ') | |
| self.col = self.col + 1 | |
| if tag == 'tr': | |
| write('}') | |
| self.col = 0 | |
| # skip header | |
| if tag == 'tr': | |
| self.row = self.row + 1 | |
| def handle_data(self, data): | |
| if self.row: | |
| write(data.strip()) | |
| parser = MyHTMLParser2() | |
| write('[') | |
| for i in range(1,13): | |
| html = get_page_raw_data(i) | |
| parser.feed(html) | |
| if i < 12: | |
| write(', ') | |
| write(']') | |
| #[{"town": "東區", "village": "東勢里", "name" : "林錦全"}, ...] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/python | |
| #-*- coding: utf-8 -*- | |
| import urllib2 | |
| import cookielib | |
| import sys | |
| from HTMLParser import HTMLParser | |
| AXE_URL = 'http://axe-level-1.herokuapp.com/lv3' | |
| cj = cookielib.CookieJar() | |
| opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj)) | |
| urllib2.install_opener(opener) | |
| def get_page_raw_data(axe_url='%s/?page='%AXE_URL, page_num='next'): | |
| url = axe_url + page_num | |
| response = urllib2.urlopen(url) | |
| html = response.read() | |
| return html | |
| def write(value=''): | |
| sys.stdout.write(str(value)) | |
| class MyHTMLParser2(HTMLParser): | |
| row, col = 0, 0 | |
| fm = ['"town": "', '"village": "', '"name" : "'] | |
| def handle_starttag(self, tag, attrs): | |
| if self.row: | |
| if tag == 'tr': | |
| if self.row > 1: | |
| write(', ') | |
| write('{') | |
| if tag == 'td': | |
| write(self.fm[self.col]) | |
| def handle_endtag(self, tag): | |
| if tag == 'table': | |
| self.row = 0 | |
| if self.row: | |
| if tag == 'td': | |
| if self.col == 2: | |
| write('"') | |
| else: | |
| write('", ') | |
| self.col = self.col + 1 | |
| if tag == 'tr': | |
| write('}') | |
| self.col = 0 | |
| # skip header | |
| if tag == 'tr': | |
| self.row = self.row + 1 | |
| def handle_data(self, data): | |
| if self.row: | |
| write(data.strip()) | |
| parser = MyHTMLParser2() | |
| write('[') | |
| html = get_page_raw_data(axe_url=AXE_URL, page_num='') | |
| parser.feed(html) | |
| write(', ') | |
| for i in range(1,76): | |
| html = get_page_raw_data() | |
| parser.feed(html) | |
| if i < 75: | |
| write(', ') | |
| write(']') | |
| #[{"town": "東區", "village": "東勢里", "name" : "林錦全"}, ...] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/python | |
| #-*- coding: utf-8 -*- | |
| import urllib2 | |
| import cookielib | |
| import sys | |
| import random | |
| import time | |
| from HTMLParser import HTMLParser | |
| AXE_URL = 'http://axe-level-4.herokuapp.com/lv4' | |
| UA = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:27.0) Gecko/20100101 Firefox/27.0' | |
| REF = lambda num: '%s/?page=%s' % (AXE_URL, num) | |
| cj = cookielib.CookieJar() | |
| opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj)) | |
| urllib2.install_opener(opener) | |
| def get_page_raw_data(ref=None, axeurl='%s/?page=1' % AXE_URL): | |
| url = axeurl | |
| time.sleep(random.random()*2**2) | |
| request = urllib2.Request(url) | |
| request.add_header('User-Agent', UA) | |
| if ref: | |
| request.add_header('Referer', ref) | |
| response = urllib2.urlopen(request) | |
| html = response.read() | |
| return html | |
| def write(value=''): | |
| sys.stdout.write(str(value)) | |
| class MyHTMLParser4(HTMLParser): | |
| row, col = 0, 0 | |
| fm = ['"town": "', '"village": "', '"name" : "'] | |
| def handle_starttag(self, tag, attrs): | |
| if self.row: | |
| if tag == 'tr': | |
| if self.row > 1: | |
| write(', ') | |
| write('{') | |
| if tag == 'td': | |
| write(self.fm[self.col]) | |
| def handle_endtag(self, tag): | |
| if tag == 'table': | |
| self.row = 0 | |
| if self.row: | |
| if tag == 'td': | |
| if self.col == 2: | |
| write('"') | |
| else: | |
| write('", ') | |
| self.col = self.col + 1 | |
| if tag == 'tr': | |
| write('}') | |
| self.col = 0 | |
| # skip header | |
| if tag == 'tr': | |
| self.row = self.row + 1 | |
| def handle_data(self, data): | |
| if self.row: | |
| write(data.strip()) | |
| parser = MyHTMLParser4() | |
| write('[') | |
| ref = AXE_URL+'/' | |
| html = get_page_raw_data(axeurl=ref) | |
| parser.feed(html) | |
| write(', ') | |
| html = get_page_raw_data(ref, axeurl=REF(2)) | |
| parser.feed(html) | |
| write(', ') | |
| for i in range(3, 24): | |
| axeurl=REF(i) | |
| html = get_page_raw_data(ref=REF(i-1), axeurl=axeurl) | |
| parser.feed(html) | |
| write(', ') | |
| html = get_page_raw_data(ref=REF(23), axeurl=REF(24)) | |
| parser.feed(html) | |
| write(']') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment