X-Git-Url: http://git.tdb.fi/?a=blobdiff_plain;f=scrape-item-data.py;h=f5f67b488593515d4b708d3d30351d5df0cd9170;hb=363461fc5eb9000e386c881cad8d9aed39478f83;hp=3174a270c903491d7adbf6362c1d64cf9647a0e3;hpb=2b871ff878516456579f287626c7efb35508cab9;p=poefilter.git

diff --git a/scrape-item-data.py b/scrape-item-data.py
index 3174a27..f5f67b4 100755
--- a/scrape-item-data.py
+++ b/scrape-item-data.py
@@ -3,6 +3,7 @@
 import requests
 import html.parser
 import codecs
+import argparse
 
 class Item:
 	def __init__(self, name, kind):
@@ -109,7 +110,7 @@ class ItemDataParser(html.parser.HTMLParser):
 		self.in_items_table = False
 		self.column = 0
 		self.in_cell = False
-		self.items = {}
+		self.items = []
 		self.current_item = None
 		self.in_heading = False
 		self.headings = []
@@ -145,7 +146,7 @@ class ItemDataParser(html.parser.HTMLParser):
 			self.in_cell = False
 		elif tag=="tr":
 			if self.current_item and self.mod_row:
-				for it in self.items.values():
+				for it in self.items:
 					self.current_item.check_upgrade(it)
 		elif tag=="h1":
 			self.in_heading = False
@@ -175,7 +176,7 @@ class ItemDataParser(html.parser.HTMLParser):
 			else:
 				if self.column==2:
 					self.current_item = self.create_item(data, self.current_heading)
-					self.items[data] = self.current_item
+					self.items.append(self.current_item)
 				elif self.column==3:
 					self.current_item.droplevel = int(data)
 				elif self.column>=4:
@@ -237,11 +238,59 @@ def write_best_category(out, prefix, items, steps):
 		out.write("\t\t};\n")
 	out.write("\t};\n};\n")
 
+def print_debug(items):
+	upgrades = set()
+	for it in items:
+		for u in it.upgrades.values():
+			if u:
+				upgrades.add(u.name)
+
+	printed = set()
+
+	queue = []
+	while 1:
+		for it in items:
+			if it.name not in upgrades and it.name not in printed:
+				queue.append(it)
+				break
+
+		if not queue:
+			break
+
+		while queue:
+			it = queue.pop(0)
+			if it.name in printed:
+				continue
+			printed.add(it.name)
+
+			print(it.name)
+			print("  level: {}".format(it.droplevel))
+			if isinstance(it, Armor):
+				print("  armor: {}".format(it.armor))
+				print("  evasion: {}".format(it.evasion))
+				print("  energy shield: {}".format(it.energy_shield))
+			elif isinstance(it, Weapon):
+				print("  dps: {}".format(it.dps))
+			for n, v in it.mods.items():
+				print("  {}: {}".format(n, v))
+			for t, u in it.upgrades.items():
+				if u:
+					print("  upgrade {}: {}".format(t, u.name))
+					if u.name not in printed:
+						queue.insert(0, u)
+
 def main():
+	parser = argparse.ArgumentParser()
+	parser.add_argument("-g", "--debug", action="store_true", dest="debug")
+	args = parser.parse_args()
+
 	r = requests.get("https://www.pathofexile.com/item-data/armour")
 	p = ArmorDataParser()
 	p.feed(codecs.decode(r.content, r.encoding))
 
+	if args.debug:
+		print_debug(p.items)
+
 	types = {"robe": lambda i: (not i.armor and not i.evasion and i.energy_shield),
 		"cloth": lambda i: (not i.armor and i.evasion and i.energy_shield),
 		"leather": lambda i: (not i.armor and i.evasion and not i.energy_shield),
@@ -252,27 +301,10 @@ def main():
 	out = open("armor.txt", "w")
 
 	for t, f in types.items():
-		items = [i for i in p.items.values() if f(i)]
+		items = [i for i in p.items if f(i)]
 
 		for i in range(1, 3):
 			write_best_category(out, "armor.{}".format(t), items, i)
-			"""out.write('category "armor.{}.{}_at_level"\n'.format(t, best[i-1]))
-			out.write("{\n\tor\n\t{\n")
-			for it in items:
-				next_level = 0
-				n = it.name
-				for k in range(i):
-					n = p.upgrades.get(n, "")
-				if n:
-					next_level = p.items[n].droplevel
-				if next_level:
-					out.write("\t\tand\n\t\t{\n")
-					out.write('\t\t\tbase_type "{}";\n'.format(it.name))
-					out.write("\t\t\tmax_item_level {};\n".format(next_level-1))
-					out.write("\t\t};\n")
-				else:
-					out.write('\t\tbase_type "{}";\n'.format(it.name))
-			out.write("\t};\n};\n")"""
 
 		out.write('category "armor.{}"\n'.format(t))
 		out.write("{\n\tor\n\t{\n")
@@ -289,10 +321,13 @@ def main():
 	p = WeaponDataParser()
 	p.feed(codecs.decode(r.content, r.encoding))
 
+	if args.debug:
+		print_debug(p.items)
+
 	out = open("weapons.txt", "w")
 
 	for h in p.headings:
-		items = [i for i in p.items.values() if i.kind==h]
+		items = [i for i in p.items if i.kind==h]
 
 		for i in range(1, 3):
 			write_best_category(out, "weapon.{}".format(h.lower().replace(' ', '_')), items, i)