We Keep Coding

Scraping data beach volleyball on multiple pages

I am trying to scrape all the possible data from this webpage Gstaad 2017
Here is my code:
import requests
from bs4 import BeautifulSoup
import pandas as pd
import re
from selenium.webdriver.support.ui import Select
#Starts the driver and goes to our starting webpage
driver = webdriver.Chrome( "C:/Users/aldi/Downloads/chromedriver.exe")
driver.get('http://www.bvbinfo.com/Tournament.asp?ID=3294&Process=Matches')
#Imports HTML into python
page = requests.get('http://www.bvbinfo.com/Tournament.asp?ID=3294&Process=Matches')
soup = BeautifulSoup(driver.page_source, 'lxml')
stages = soup.find_all('div')
stages = driver.find_elements_by_class_name('clsTournBracketHeader')[-1].text
#TODO the first row (country quota matches) has no p tag and therefore it is not included in the data
rows = []
paragraphs = []
empty_paragraphs = []
for x in soup.find_all('p'):
if len(x.get_text(strip=True)) != 0:
paragraph = x.extract()
paragraphs.append(paragraph)
if len(x.get_text(strip=True)) == 0:
empty_paragraph = x.extract()
empty_paragraphs.append(empty_paragraph)
# players
home_team_player_1 = ''
home_team_player_2 = ''
away_team_player_1 = ''
away_team_player_2 = ''
for i in range(0, len(paragraphs)):
#round and satege of the competition
round_n= paragraphs[i].find('u').text
paragraph_rows = paragraphs[i].text.split('\n')[1:-1]
counter = 0
for j in range(0,len(paragraph_rows)):
#TODO tournament info, these can vary from tournament to tournament
tournament_info = soup.find('td', class_ = 'clsTournHeader').text.strip().split()
tournament_category = [' '.join(tournament_info[0 : 2])][0]
tournament_prize_money = tournament_info[2]
#TODO tournament city can also have two elements, not just one
tournament_city = tournament_info[3]
tournament_year = tournament_info[-1]
tournament_days = tournament_info[-2][:-1].split("-")
tournament_starting_day = tournament_days[0]
tournament_ending_day = tournament_days[-1]
tournament_month = tournament_info[-3]
tournament_stars = [' '.join(tournament_info[5 : 7])][0]
players = paragraphs[i].find_all('a', {'href':re.compile('.*player.*')})
home_team_player_1 = players[counter+0].text
home_team_player_2 = players[counter+1].text
away_team_player_1 = players[counter+2].text
away_team_player_2 = players[counter+3].text
#matches
match= paragraph_rows[j].split(":")[0].split()[-1].strip()
#nationalities
nationalities = ["United", "States"]
if paragraph_rows[j].split("def.")[0].split("/")[1].split("(")[0].split(" ")[3] in nationalities:
home_team_country = "United States"
else:
home_team_country = paragraph_rows[j].split("def.")[0].split("/")[1].split("(")[0].split(" ")[-2]
if paragraph_rows[j].split("def.")[1].split("/")[1].split(" ")[3] in nationalities:
away_team_country = "United States"
else:
away_team_country = paragraph_rows[j].split("def.")[1].split("/")[1].split("(")[0].split(" ")[-2]
parentheses = re.findall(r'\(.*?\)', paragraph_rows[j])
if "," in parentheses[0]:
home_team_ranking = parentheses[0].split(",")[0]
home_team_ranking = home_team_ranking[1:-1]
home_team_qualification_round = parentheses[0].split(",")[1]
home_team_qualification_round = home_team_qualification_round[1:-1]
else:
home_team_ranking = parentheses[0].split(",")[0]
home_team_ranking = home_team_ranking[1:-1]
home_team_qualification_round = None
if "," in parentheses[1]:
away_team_ranking = parentheses[1].split(",")[0]
away_team_ranking = away_team_ranking[1:-1]
away_team_qualification_round = parentheses[1].split(",")[1]
away_team_qualification_round = away_team_qualification_round[1:-1]
else:
away_team_ranking = parentheses[1].split(",")[0]
away_team_ranking = away_team_ranking[1:-1]
match_duration = parentheses[2]
match_duration = match_duration[1:-1]
away_team_qualification_round = None
# sets
sets = re.findall(r'\).*?\(', paragraph_rows[j])
sets = sets[1][1:-1]
if len(sets.split(",")) == 2:
score_set1 = sets.split(",")[0]
score_set2 = sets.split(",")[1]
score_set3 = None
if len(sets.split(",")) == 3:
score_set1 = sets.split(",")[0]
score_set2 = sets.split(",")[1]
score_set3 = sets.split(",")[2]
row = { " home_team_player_1 ": home_team_player_1 ,
" home_team_player_2": home_team_player_2,
"away_team_player_1": away_team_player_1,
"away_team_player_2":away_team_player_1,
"match": match,
"home_team_country":home_team_country,
"away_team_country": away_team_country,
"home_team_ranking": home_team_ranking,
"away_team_ranking": away_team_ranking,
"match_duration": match_duration,
"home_team_qualification_round": home_team_qualification_round,
"away_team_qualification_round": away_team_qualification_round,
"score_set1":score_set1,
"score_set2":score_set2,
"score_set3":score_set3,
"tournament_category": tournament_category,
"tournament_prize_money": tournament_prize_money,
"tournament_city": tournament_city,
"tournament_year": tournament_year,
"tournament_starting_day": tournament_starting_day,
"tournament_ending_day":tournament_ending_day,
"tournament_month":tournament_month,
"tournament_stars":tournament_stars,
"round_n": round_n
}
counter += 4
rows.append(row)
data = pd.DataFrame(rows)
data.to_csv("beachvb.csv", index = False)
I am not really experienced in web scraping. I have just started as a self-taught and find the HTML source code quite messy and poorly structured.
I want to improve my code in two ways:
Include all the missing matches (country quota matches, semifinals, bronze medal, and gold medal) and the respective category for each match (country quota matches, pool, winner's bracket, semifinals, bronze medal, and gold medal)
iterate the code for more years and tournaments from the dropdown menu at the top of the webpage
I have tried to iterate through different years but my code does not work
tournament_years = {"FIVB 2015", "FIVB 2016"}
dfs = []
for year in tournament_years:
# select desired tournament
box_year = Select(driver.find_element_by_xpath("/html/body/table[3]/tbody/tr/td/table[1]/tbody/tr[1]/td[2]/select"))
box_year.select_by_visible_text(year)
box_matches = Select(driver.find_element_by_xpath("/html/body/table[3]/tbody/tr/td/table[1]/tbody/tr[2]/td[2]/select"))
box_matches.select_by_visible_text("Matches")
The main idea was to create a list of dataframes for each year and each tournament by adding a new loop at the beginning of the code.
If someone has a better idea and technique to do so, it is really appreciated!

How to make it like make it's process of adding automatically based on keyword count

I am trying to make a form where if I input a medicine's name, it will show the solution of the medicine serially. But it is kind of limited bythe way I'm making it like more lines I'll code more spaces they will get to have the number of feedback. It would be great if you could help me to make something short but have the infinity process like loop.
df = pd.DataFrame({'FEVER':['NAPA_PLUS','JERIN','PARASITAMOL'],
'GASTRIC':['SECLO40','SECLO20','ANTACID'],
'WATERINESS':['ORSALINE','TESTY_SALINE','HOME_MADE_SALINE']})
def word_list(text):
return list(filter(None, re.split('\W+', text)))
session = raw_input("INPUT THE NAME OF THE MEDICINES ONE BY ONE BY KEEPING SPACE:")
feedback = session
print(word_list(feedback))
dff = pd.DataFrame({'itemlist':[feedback]})
dff['1'] = dff['itemlist'].astype(str).str.split().str[0]
dff['2'] = dff['itemlist'].astype(str).str.split().str[1]
dff['3'] = dff['itemlist'].astype(str).str.split().str[2]
dff['4'] = dff['itemlist'].astype(str).str.split().str[3]
dff['5'] = dff['itemlist'].astype(str).str.split().str[4]
for pts1 in dff['1']:
pts1 = df.columns[df.isin([pts1]).any()]
for pts2 in dff['2']:
pts2 = df.columns[df.isin([pts2]).any()]
for pts3 in dff['3']:
pts3 = df.columns[df.isin([pts3]).any()]
for pts4 in dff['4']:
pts4 = df.columns[df.isin([pts4]).any()]
for pts5 in dff['5']:
pts5 = df.columns[df.isin([pts5]).any()]

This wraps your repeated code into two loops:
...
dff = pd.DataFrame({'itemlist':[feedback]})
limit = 5
for i in xrange(limit):
name = str(i+1)
dff[name] = dff['itemlist'].astype(str).str.split().str[i]
for pts in dff[name]:
pts = df.columns[df.isin([pts]).any()]

Appending a python dict from a while loop gives unexpected results

The max number of records in my input json is 100 however there is a paging-next link that provides the next 100 records. Below is what I have but it returns a dict with only 100 entries- I know there are more- How should I modify this function to get all the records?
def process_comment_json(comment_json):
post_comment_dict = dict()
next_links = list()
if 'comments' in comment_json.keys():
try:
for y in comment_json['comments']['data']:
post_id = comment_json['id']
commentor_name = y['from']['name']
commentor_id = y['from']['id']
created_time = y['created_time']
message = remove_non_ascii(y['message'])
sentiment = return_sentiment_score(message)
post_comment_dict[commentor_id] = {'commentor_name':commentor_name,\
'created_time':created_time, 'message':message,\
'sentiment':sentiment}
except:
print("malformed data, skipping this comment in round1")
if 'next' in comment_json['comments']['paging']:
print('found_next appending')
next_links.append(comment_json['comments']['paging']['next'])
else:
return post_comment_dict
while next_links:
print("processing next_links")
print("current len of post_comment_dict is:", len(post_comment_dict))
for next_link in next_links:
t = requests.get(next_link)
nl_json = t.json()
next_links.pop()
if "data" in list(nl_json.keys()):
for record in nl_json['data']:
try:
for y in comment_json['comments']['data']:
post_id = comment_json['id']
commentor_name = y['from']['name']
commentor_id = y['from']['id']
created_time = y['created_time']
message = remove_non_ascii(y['message'])
sentiment = return_sentiment_score(message)
post_comment_dict[commentor_id] = {'commentor_name':commentor_name,\
'created_time':created_time, 'message':message,\
'sentiment':sentiment}
except:
print("malformed data, skipping this comment from the next_links list")
if 'next' in comment_json['comments']['paging']:
print('found_next appending')
next_links.append(comment_json['comments']['paging']['next'])
else:
return post_comment_dict

List comes back as empty when retrieveing data from website ; Python

I am trying to parse data from a website by inserting the data into a list, but the list comes back empty.
url =("http://www.releasechimps.org/resources/publication/whos-there-md- anderson")
http = urllib3.PoolManager()
r = http.request('Get',url)
soup = BeautifulSoup(r.data,"html.parser")
#print(r.data)
loop = re.findall(r'<td>(.*?)</td>',str(r.data))
#print(str(loop))
newLoop = str(loop)
#print(newLoop)
for x in range(1229):
if "\\n\\t\\t\\t\\t" in loop[x]:
loop[x] = loop[x].replace("\\n\\t\\t\\t\\t","")
list0_v2.append(str(loop[x]))
print(loop[x])
print(str(list0_v2))

Edit: Didn't really have anything else going on, so I made your data format into a nice list of dictionaries. There's a weird <td height="26"> on monkey 111, so I had to change the regex slightly.
Hope this helps you, I did it cause I care about the monkeys man.
import html
import re
import urllib.request
list0_v2 = []
final_list = []
url = "http://www.releasechimps.org/resources/publication/whos-there-md-anderson"
data = urllib.request.urlopen(url).read()
loop = re.findall(r'<td.*?>(.*?)</td>', str(data))
for item in loop:
if "\\n\\t\\t\\t\\t" or "em>" in item:
item = item.replace("\\n\\t\\t\\t\\t", "").replace("<em>", "")\
.replace("</em>", "")
if " " == item:
continue
list0_v2.append(item)
n = 1
while len(list0_v2) != 0:
form = {"n":0, "name":"", "id":"", "gender":"", "birthdate":"", "notes":""}
try:
if list0_v2[5][-1] == '.':
numb, name, ids, gender, birthdate, notes = list0_v2[0:6]
form["notes"] = notes
del(list0_v2[0:6])
else:
raise Exception('foo')
except:
numb, name, ids, gender, birthdate = list0_v2[0:5]
del(list0_v2[0:5])
form["n"] = int(numb)
form["name"] = html.unescape(name)
form["id"] = ids
form["gender"] = gender
form["birthdate"] = birthdate
final_list.append(form)
n += 1
for li in final_list:
print("{:3} {:10} {:10} {:3} {:10} {}".format(li["n"], li["name"], li["id"],\
li["gender"], li["birthdate"], li["notes"]))

create and assign subcategories in revit using python

I have a question for some of you who are familiar with the Revit API and python:
I’ve been using the spring nodes package in dynamo to create a rather large series of freeform objects each in their own family. The way that the FamilyInstance.ByGeometry works, it takes a list of solids and creates a family instance for each using a template family file. The result is quite good. (spring nodes can be found here: https://github.com/dimven/SpringNodes)
However, the drawback is that that now I have roughly 200 separate instances, so to make changes to each is rather painful. I thought at first it would be possible to use dynamo to create a new subcategory and set the solid inside each family instance to this new subcategory. Unfortunately, I realized this is not possible since dynamo cannot be open in two different Revit environments simultaneously (the project I am working in and each instance of the family). This leads me to look to see if I can do this using python.
I have used python in rhino and can get along pretty well, I am still learning the Revit API however. But basically my idea would be to:
1. select a series of family instances in the Revit project environment
2. loop through each instance
3. save it to a specified location
4. create a new subcategory in each family instances (the subcategory would the same for all the selected family instances)
5. select the solid in each in instance
6. set the solid to this newly created subcategory
7. close the family instance and save
My question for you is does this sound like it is achievable based on your knowledge of the Revit API?
Many thanks for your time and advice.
UPDATE:
I've found a section in the revit api that describes what i'm looking to do: http://help.autodesk.com/view/RVT/2015/ENU/?guid=GUID-FBF9B994-ADCB-4679-B50B-2E9A1E09AA48
I've made a first pass at inserting this into the python code of the dynamo node. The rest of the code works fine except for the new section im adding (see below). Please excuse the variables, I am simply keeping with logic of the original author of the code i am hacking:
(Note: the variables come in are in arrays)
#set subcategory
try:
#create new sucategory
fam_subcat = famdoc.Settings.Categories.NewSubcategory(fam_cat, get_Item(subcat1.Name))
#assign the mataterial(fam_mat.Id) to the subcategory
fam_subcat.Material = famdoc.GetElement(fam_mat.Id)
#assign the subcategory to the element (s2)
s2.Subcategory = fam_subcat
except: pass
Any help or advice with this section of code would be much appreciated.
UPDATE:
See full code below for context of the section in question:
#Copyright(c) 2015, Dimitar Venkov
# #5devene, dimitar.ven#gmail.com
import clr
import System
from System.Collections.Generic import *
pf_path = System.Environment.GetFolderPath(System.Environment.SpecialFolder.ProgramFilesX86)
import sys
sys.path.append("%s\IronPython 2.7\Lib" %pf_path)
import traceback
clr.AddReference('ProtoGeometry')
from Autodesk.DesignScript.Geometry import *
clr.AddReference("RevitServices")
import RevitServices
from RevitServices.Persistence import DocumentManager
from RevitServices.Transactions import TransactionManager
doc = DocumentManager.Instance.CurrentDBDocument
app = DocumentManager.Instance.CurrentUIApplication.Application
clr.AddReference("RevitAPI")
from Autodesk.Revit.DB import *
from Autodesk.Revit.DB.Structure import StructuralType
clr.AddReference("RevitNodes")
import Revit
clr.ImportExtensions(Revit.Elements)
clr.ImportExtensions(Revit.GeometryConversion)
def tolist(obj1):
if hasattr(obj1,"__iter__"): return obj1
else: return [obj1]
def output1(l1):
if len(l1) == 1: return l1[0]
else: return l1
def PadLists(lists):
len1 = max([len(l) for l in lists])
for i in xrange(len(lists)):
if len(lists[i]) == len1:
continue
else:
len2 = len1 - len(lists[i])
for j in xrange(len2):
lists[i].append(lists[i][-1])
return lists
class FamOpt1(IFamilyLoadOptions):
def __init__(self):
pass
def OnFamilyFound(self,familyInUse, overwriteParameterValues):
return True
def OnSharedFamilyFound(self,familyInUse, source, overwriteParameterValues):
return True
geom = tolist(IN[0])
fam_path = IN[1]
names = tolist(IN[2])
category = tolist(IN[3])
material = tolist(IN[4])
isVoid = tolist(IN[5])
subcategory = tolist(IN[6])
isRvt2014 = False
if app.VersionName == "Autodesk Revit 2014": isRvt2014 = True
units = doc.GetUnits().GetFormatOptions(UnitType.UT_Length).DisplayUnits
factor = UnitUtils.ConvertToInternalUnits(1,units)
acceptable_views = ["ThreeD", "FloorPlan", "EngineeringPlan", "CeilingPlan", "Elevation", "Section"]
origin = XYZ(0,0,0)
str_typ = StructuralType.NonStructural
def NewForm_background(s1, name1, cat1, isVoid1, mat1, subcat1):
t1 = TransactionManager.Instance
TransactionManager.ForceCloseTransaction(t1)
famdoc = doc.Application.NewFamilyDocument(fam_path)
message = None
temp_path = System.IO.Path.GetTempPath()
sat_path = "%s%s.sat" % (temp_path, name1)
try:
if factor != 1:
s1 = s1.Scale(factor)
sat1 = Geometry.ExportToSAT(s1, sat_path)
satOpt = SATImportOptions()
satOpt.Placement = ImportPlacement.Origin
satOpt.Unit = ImportUnit.Foot
view_fec = FilteredElementCollector(famdoc).OfClass(View)
view1 = None
for v in view_fec:
if str(v.ViewType) in acceptable_views:
view1 = v
break
t1.EnsureInTransaction(famdoc)
satId = famdoc.Import(sat1, satOpt, view1)
opt1 = Options()
opt1.ComputeReferences = True
el1 = famdoc.GetElement(satId)
geom1 = el1.get_Geometry(opt1)
enum = geom1.GetEnumerator()
enum.MoveNext()
geom2 = enum.Current.GetInstanceGeometry()
enum2 = geom2.GetEnumerator()
enum2.MoveNext()
s1 = enum2.Current
famdoc.Delete(satId)
TransactionManager.ForceCloseTransaction(t1)
System.IO.File.Delete(sat_path)
except:
message = traceback.format_exc()
pass
if message == None:
try:
save_path = "%s%s.rfa" % (temp_path, name1)
SaveAsOpt = SaveAsOptions()
SaveAsOpt.OverwriteExistingFile = True
t1.EnsureInTransaction(famdoc)
#set the category
try:
fam_cat = famdoc.Settings.Categories.get_Item(cat1.Name)
famdoc.OwnerFamily.FamilyCategory = fam_cat
except: pass
s2 = FreeFormElement.Create(famdoc,s1)
if isVoid1:
void_par = s2.get_Parameter("Solid/Void")
void_par.Set(1)
void_par2 = famdoc.OwnerFamily.get_Parameter("Cut with Voids When Loaded")
void_par2.Set(1)
else: #voids do not have a material value
try:
mat_fec = FilteredElementCollector(famdoc).OfClass(Material)
for m in mat_fec:
if m.Name == mat1:
fam_mat = m
break
mat_par = s2.get_Parameter("Material")
mat_par.Set(fam_mat.Id)
except: pass
#set subcategory
try:
#create new sucategory
fam_subcat = document.Settings.Categories.NewSubcategory(document.OwnerFamily.FamilyCategory, get_Item(subcat1.Name))
#assign the mataterial(fam_mat.Id) to the subcategory
fam_subcat.Material = famdoc.GetElement(fam_mat.Id)
#assign the subcategory to the element (s2)
s2.Subcategory = fam_subcat
except: pass
TransactionManager.ForceCloseTransaction(t1)
famdoc.SaveAs(save_path, SaveAsOpt)
family1 = famdoc.LoadFamily(doc, FamOpt1())
famdoc.Close(False)
System.IO.File.Delete(save_path)
symbols = family1.Symbols.GetEnumerator()
symbols.MoveNext()
symbol1 = symbols.Current
t1.EnsureInTransaction(doc)
if not symbol1.IsActive: symbol1.Activate()
inst1 = doc.Create.NewFamilyInstance(origin, symbol1, str_typ)
TransactionManager.ForceCloseTransaction(t1)
return inst1.ToDSType(False), family1.ToDSType(False)
except:
message = traceback.format_exc()
return message
else:
return message
def NewForm_background_R16(s1, name1, cat1, isVoid1, mat1, subcat1):
t1 = TransactionManager.Instance
TransactionManager.ForceCloseTransaction(t1)
famdoc = doc.Application.NewFamilyDocument(fam_path)
message = None
temp_path = System.IO.Path.GetTempPath()
sat_path = "%s%s.sat" % (temp_path, name1)
try:
if factor != 1:
s1 = s1.Scale(factor)
sat1 = Geometry.ExportToSAT(s1, sat_path)
satOpt = SATImportOptions()
satOpt.Placement = ImportPlacement.Origin
satOpt.Unit = ImportUnit.Foot
view_fec = FilteredElementCollector(famdoc).OfClass(View)
view1 = None
for v in view_fec:
if str(v.ViewType) in acceptable_views:
view1 = v
break
t1.EnsureInTransaction(famdoc)
satId = famdoc.Import(sat1, satOpt, view1)
opt1 = Options()
opt1.ComputeReferences = True
el1 = famdoc.GetElement(satId)
geom1 = el1.get_Geometry(opt1)
enum = geom1.GetEnumerator()
enum.MoveNext()
geom2 = enum.Current.GetInstanceGeometry()
enum2 = geom2.GetEnumerator()
enum2.MoveNext()
s1 = enum2.Current
famdoc.Delete(satId)
TransactionManager.ForceCloseTransaction(t1)
System.IO.File.Delete(sat_path)
except:
message = traceback.format_exc()
pass
if message == None:
try:
save_path = "%s%s.rfa" % (temp_path, name1)
SaveAsOpt = SaveAsOptions()
SaveAsOpt.OverwriteExistingFile = True
t1.EnsureInTransaction(famdoc)
#set the category
try:
fam_cat = famdoc.Settings.Categories.get_Item(cat1.Name)
famdoc.OwnerFamily.FamilyCategory = fam_cat
except: pass
s2 = FreeFormElement.Create(famdoc,s1)
if isVoid1:
void_par = s2.LookupParameter("Solid/Void")
void_par.Set(1)
void_par2 = famdoc.OwnerFamily.LookupParameter("Cut with Voids When Loaded")
void_par2.Set(1)
else: #voids do not have a material value
try:
mat_fec = FilteredElementCollector(famdoc).OfClass(Material)
for m in mat_fec:
if m.Name == mat1:
fam_mat = m
break
mat_par = s2.LookupParameter("Material")
mat_par.Set(fam_mat.Id)
except: pass
#apply same subcategory code as before
#set subcategory
try:
#create new sucategory
fam_subcat = famdoc.Settings.Categories.NewSubcategory(fam_cat, get_Item(subcat1.Name))
#assign the mataterial(fam_mat.Id) to the subcategory
fam_subcat.Material = famdoc.GetElement(fam_mat.Id)
#assign the subcategory to the element (s2)
s2.Subcategory = fam_subcat
except: pass
TransactionManager.ForceCloseTransaction(t1)
famdoc.SaveAs(save_path, SaveAsOpt)
family1 = famdoc.LoadFamily(doc, FamOpt1())
famdoc.Close(False)
System.IO.File.Delete(save_path)
symbols = family1.GetFamilySymbolIds().GetEnumerator()
symbols.MoveNext()
symbol1 = doc.GetElement(symbols.Current)
t1.EnsureInTransaction(doc)
if not symbol1.IsActive: symbol1.Activate()
inst1 = doc.Create.NewFamilyInstance(origin, symbol1, str_typ)
TransactionManager.ForceCloseTransaction(t1)
return inst1.ToDSType(False), family1.ToDSType(False)
except:
message = traceback.format_exc()
return message
else:
return message
if len(geom) == len(names) == len(category) == len(isVoid) == len(material) == len(subcategory):
if isRvt2014:
OUT = output1(map(NewForm_background, geom, names, category, isVoid, material, subcategory))
else:
OUT = output1(map(NewForm_background_R16, geom, names, category, isVoid, material, subcategory))
elif len(geom) == len(names):
padded = PadLists((geom, category, isVoid, material, subcategory))
p_category = padded[1]
p_isVoid = padded[2]
p_material = padded[3]
p_subcategory = padded [4]
if isRvt2014:
OUT = output1(map(NewForm_background, geom, names, p_category, p_isVoid, p_material, p_subcategory))
else:
OUT = output1(map(NewForm_background_R16, geom, names, p_category, p_isVoid, p_material, subcategory))
else: OUT = "Make sure that each geometry\nobject has a unique family name."
Update:
Was able to get it working:
try:
#create new sucategory
fam_subcat = famdoc.Settings.Categories.NewSubcategory(famdoc.OwnerFamily.FamilyCategory, subcat1)
#assign the mataterial(fam_mat.Id) to the subcategory
#fam_subcat.Material = famdoc.GetElement(fam_mat.Id)
#assign the subcategory to the element (s2)
s2.Subcategory = fam_subcat
except: pass

As I answered on your initial query per email, what you are aiming for sounds perfectly feasible to me in the Revit API. Congratulations on getting as far as you have. Looking at the link to the Revit API help file and developer guide that you cite above, it seems that the code has to be executed in the family document while defining the family. The context in which you are trying to execute it is not clear. Have you used EditFamily to open the family definition document? What context are you executing in?