annotate V1/test1.py @ 10:85c9aa9d90c5

implement refactor and present results, to output to csv

#!/usr/bin/env python

import requests
import re
from HTMLParser import HTMLParser
# from lxml import html
from bs4 import BeautifulSoup


url = "https://horoscopes.astro-seek.com/calculate-love-compatibility/?send_calculation=1&muz_narozeni_den=1&muz_narozeni_mesic=1&muz_narozeni_rok=1970&muz_narozeni_hodina=00&muz_narozeni_minuta=00&muz_narozeni_city=London%2C+United+Kingdom&muz_narozeni_mesto_hidden=London&muz_narozeni_stat_hidden=GB&muz_narozeni_podstat_kratky_hidden=England&muz_narozeni_podstat_hidden=England&muz_narozeni_podstat2_kratky_hidden=Greater+London&muz_narozeni_podstat3_kratky_hidden=undefined&muz_narozeni_input_hidden=&muz_narozeni_sirka_stupne=51&muz_narozeni_sirka_minuty=30&muz_narozeni_sirka_smer=0&muz_narozeni_delka_stupne=0&muz_narozeni_delka_minuty=8&muz_narozeni_delka_smer=1&muz_narozeni_timezone_form=auto&muz_narozeni_timezone_dst_form=auto&send_calculation=1&zena_narozeni_den=1&zena_narozeni_mesic=1&zena_narozeni_rok=1970&zena_narozeni_hodina=00&zena_narozeni_minuta=00&zena_narozeni_city=Berlin%2C+Germany&zena_narozeni_mesto_hidden=Berlin&zena_narozeni_stat_hidden=DE&zena_narozeni_podstat_kratky_hidden=Berlin&zena_narozeni_podstat_hidden=Berlin&zena_narozeni_podstat2_kratky_hidden=undefined&zena_narozeni_podstat3_kratky_hidden=undefined&zena_narozeni_input_hidden=&zena_narozeni_sirka_stupne=52&zena_narozeni_sirka_minuty=31&zena_narozeni_sirka_smer=0&zena_narozeni_delka_stupne=13&zena_narozeni_delka_minuty=24&zena_narozeni_delka_smer=0&zena_narozeni_timezone_form=auto&zena_narozeni_timezone_dst_form=auto&switch_interpretations=0&house_system=placidus&uhel_orbis=#tabs_redraw"
url = 'https://horoscopes.astro-seek.com/calculate-love-compatibility/'
payload = {'?send_calculation':'1','muz_narozeni_den':'25','muz_narozeni_mesic':'6','muz_narozeni_rok':'1988','muz_narozeni_hodina':'00','muz_narozeni_minuta':'00','muz_narozeni_city':'London%2C+United+Kingdom','zena_narozeni_den':'14','zena_narozeni_mesic':'3','zena_narozeni_rok':'1995','zena_narozeni_hodina':'00','zena_narozeni_minuta':'00'}
 # {'muz_narozeni_den':'1','muz_narozeni_mesic':'1','muz_narozeni_rok':'1970'}

# GET
r = requests.get(url)
# # GET with params in URL
r = requests.get(url, params=payload)

# Response, status etc
# print r.text.encode('utf-8')
# tree = html.fromstring(r.content)
# tcTable = tree.xpath('//div[@class="detail-rozbor-clanek"]/strong/text()')
# print tcTable

soup = BeautifulSoup(r.content, 'lxml')
tcCell = soup.find_all('div', attrs={'class':'tc'})
# print tcCell


for cell in tcCell:
	person = dict()
	tableCell = cell.find_all('td');
	if len(tableCell) > 2:
		C = tableCell[0].strong.contents[0].encode('utf-8')
		D = tableCell[2].strong.contents[0].encode('utf-8')
		print (C,D)
		A = re.search("\/>(.*)<br/>.*\(([0-9]*)\\xc2\\xb0([0-9]*)(.*)\)",str(tableCell[1]))
		# A0 = A.group(1)
		# A1 = A.group(2).split('\xc2\xb0')[0]
		# A2 = A.group(2).split('\xc2\xb0')[1].split('\xe2')[0]
		print (A.group(1),A.group(2),A.group(3))
		person[(C,D)] = (A.group(1),A.group(2),A.group(3))
	return person
	# 	print re.search(">, (.*), <br/>.*\(([0-9]*)\\xb([0-9]*)\\u",valueCell.contents.encode('utf-8'))
	# except IndexError:
	# 	print 'te'
	# print "\n\n\n"






# # # # #

payload = {'?send_calculation':'1',
'muz_narozeni_den':'25',
'muz_narozeni_mesic':'6',
'muz_narozeni_rok':'1988',
'muz_narozeni_hodina':'00',
'muz_narozeni_minuta':'00',
'muz_narozeni_city':'London%2C+United+Kingdom',
'zena_narozeni_den':'14',
'zena_narozeni_mesic':'3',
'zena_narozeni_rok':'1995',
'zena_narozeni_hodina':'00',
'zena_narozeni_minuta':'00'}