tangotiger

with

rs as (
	select
		game_pk
		, event_inning
		, top_inning_sw
		, max(bat_score) as bat_score_end_of_inning
		, sum(event_outs) as event_outs
		

tangotiger

WITH

rs as (
	select
		instr(play_string,',',1,6) as comma_position
		, play_string
	from mytable
	where substr(play_string,1,4)='play'
)

tangotiger

import json

print("Parse start")

# http://live.nhl.com/GameData/SeasonSchedule-20152016.json
sourcefile = "C:/Users/TOM/DataNHL/original/SeasonSchedule.json"
targetfile = "C:/Users/TOM/DataNHL/final/parsed_SeasonSchedule.csv"
htmltargetfile = "C:/Users/TOM/DataNHL/final/parsed_SeasonSchedule.htm"

header_row='NHL_GAME_ID' \

tangotiger

# this takes a standard csv file and then loads it into a databse
# question: what if instead of a csv file, I had an equivalent <table><tr><td> formatted file?

sourcefile = "skeleton.csv"
dshape = discover(resource(sourcefile))

for game_id in list_game_id:
	sourcefile = "formatted_{g}.csv".format(g=game_id)
	with open(sourcefile,'r') as infile:
	    odo(sourcefile, targetfile, dshape=dshape)

tangotiger

from bs4 import BeautifulSoup
import re

print("Parse start")

first_game_id = 1  #+665
last_game_id = 668  #-2

season_id = '20152016'
subseason_id = '02'

tangotiger

# takes 2 seconds to run per infile
# source for infile: http://www.nhl.com/scores/htmlreports/20152016/PL020666.HTM

from bs4 import BeautifulSoup

print("Parse start")

first_game_id = 1  #+665
last_game_id = 668  #-2

tangotiger

from bs4 import BeautifulSoup

print("Parse start")

first_game_id = 1  #+665
last_game_id = 668 #-2

season_id = '20152016'
subseason_id = '02'
datafile_id = 'RO'

tangotiger

print("Parse start")

first_game_id = 1  #+665
last_game_id = 668 #-2

subseason_id = '02'
datafile_id = 'RO'

searchstr1 = '#</td>'
searchstr2 = 'Pos</td>'

tangotiger

import urllib.request
from bs4 import BeautifulSoup

print("Parse start")

sourcefile = "file:///C:/Users/TOM/PycharmProjects/downloadNHL/datafiles/RO020666_partial.HTM"

html = urllib.request.urlopen(sourcefile)
soup = BeautifulSoup(html, "lxml")

tangotiger

print("Parse start")

sourcefile = "C:\\Users\\TOM\\PycharmProjects\\downloadNHL\\datafiles\\schedulebyseason.htm"
targetfile = "C:\\Users\\TOM\\PycharmProjects\\downloadNHL\\datafiles\\parsed_schedulebyseason.txt"

searchstr = "recap?id="

sample_recstr = "2015020001"
reclen = len(sample_recstr)