l['Source'] = source
found = True
#if not found:
# print("- une description existe pour '" + name + "' mais pas le sommaire!");
for URLDET in URLDETS:
print(URLDET)
if MOCK_WD:
content = BeautifulSoup(open(MOCK_WD),features="lxml").body
else:
content = BeautifulSoup(urllib.request.urlopen(URLDET).read(),features="lxml").body
section = jumpTo(content, 'h1',{'class':'separator'}, u"À mains nues")
if not section:
section = jumpTo(content, 'h1',{'class':'separator'}, u"Description individuelle des armes orientales")
newObj = True
name = ""
descr = ""
source = None
sourceNext = None
for s in section:
if s.name == 'div':
for e in s.children:
if e.name == 'h2' or e.name == 'b':
if not newObj:
addInfos(liste, name, sourceNext)
l['Description'] = descr.strip()
if not source is None:
l['Source'] = source
found = True
if not found:
print("- une description existe pour '" + name +
"' mais pas le sommaire!")
if MOCK_WD:
content = BeautifulSoup(open(MOCK_WD), features="lxml").body
else:
content = BeautifulSoup(urllib.request.urlopen(URLDET).read(),
features="lxml").body
section = jumpTo(content, 'h1', {'class': 'separator'}, "Armures classiques")
newObj = True
name = ""
descr = ""
source = None
sourceNext = None
for s in section:
if s.name == 'div':
for e in s.children:
if e.name == 'h2' or e.name == 'b':
if not newObj:
addInfos(liste, name, sourceNext)
sourceNext = source
if e.name == 'h2':
'Nom', 'Classe', 'Archétype', 'Prérequis', 'Source', 'Niveau', 'Auto',
'Description', 'Référence'
]
MATCH = ['Nom', 'Classe', 'Archétype']
liste = []
print("Extraction des aptitude (astuces)...")
if MOCK_ASTUCE:
content = BeautifulSoup(open(MOCK_ASTUCE), features="lxml").body
else:
content = BeautifulSoup(urllib.request.urlopen(URL).read(),
features="lxml").body
section = jumpTo(content, 'h2', {'class': 'separator'},
"Description des astuces de ninja")
LVL = 2
astuce = {'Niveau': LVL}
newObj = False
descr = ""
source = 'AG'
for s in section:
if s.name == 'h2' and "Description des astuces de maître" in s.text:
LVL = 10
elif s.name == "table":
for td in s.find_all('td'):
for el in td.children:
if el.name == "h3":
nom = cleanSectionName(el.text)
reference = URL + el.find_next("a")['href']
# add infos to existing weapong in list
found = False
for l in liste:
for n in names:
if l['Nom'].lower() == n.lower() or l['Nom'].lower(
).startswith(n.lower()):
l['Complete'] = True
l['Description'] = descr.strip()
if not source is None:
l['Source'] = source
found = True
if not found:
print("- une description existe pour '" + name +
"' mais pas le sommaire!")
section = jumpTo(content, 'h2', {'class': 'separator'}, u"Descriptions")
if not section:
section = jumpTo(content, 'h2', {'class': 'separator'},
data["category"])
if not section:
print("No descriptions found for %s" % data["category"])
exit(1)
newObj = True
name = ""
descr = ""
source = None
sourceNext = None
for e in section:
if e.name == 'h3':
if not newObj:
FIELDS = ['Nom', 'Classe', 'Archétype', 'Prérequis', 'Source', 'Niveau', 'Auto', 'Description', 'Référence' ]
MATCH = ['Nom', 'Classe', 'Archétype']
liste = []
print("Extraction des aptitude (exploitations)...")
source = 'MCA'
if MOCK_EXPLOITATION:
content = BeautifulSoup(open(MOCK_EXPLOITATION),features="lxml").body
else:
content = BeautifulSoup(urllib.request.urlopen(URL).read(),features="lxml").body
section = jumpTo(content, 'h2',{'class':'separator'}, u"Exploitations d'arcaniste")
level = 0
for s in section:
if s.name == 'div' and s.has_attr('class') and "article_2col" in s['class']:
level = 2 if level == 0 else 11
exploitation = {'Source':source,'Niveau':level}
newObj = False
brCount = 0
descr = ""
for e in s.children:
if e.name == 'h3':
if newObj:
exploitation['Classe'] = 'Arcaniste'
#MOCK_MALEFICE = "mocks/malefices.html" # décommenter pour tester avec les maléfices pré-téléchargées
URL = "http://www.pathfinder-fr.org/Wiki/Pathfinder-RPG.mal%c3%a9fices.ashx"
FIELDS = ['Nom', 'Classe', 'Archétype', 'Prérequis', 'Source', 'Niveau', 'Auto', 'Description', 'Référence' ]
MATCH = ['Nom', 'Classe', 'Archétype']
liste = []
print("Extraction des aptitude (maléfices)...")
if MOCK_MALEFICE:
content = BeautifulSoup(open(MOCK_MALEFICE),features="lxml").body
else:
content = BeautifulSoup(urllib.request.urlopen(URL).read(),features="lxml").body
section = jumpTo(content, 'h2',{'class':'separator'}, u"Maléfices")
LVL = 1
malefice = {'Niveau':LVL}
newObj = False
descr = ""
source = 'MJRA'
for s in section:
if s.name == 'h2' and "Maléfices majeurs" in s.text:
LVL = 10
elif s.name == 'h2' and "Grands maléfices" in s.text:
LVL = 18
elif s.name == "table":
for td in s.find_all('td'):
for el in td.children:
if el.name == "h3":
if el.name == "a" or el.name == "div":
src = extractSource(el)
if src:
source = src
benediction = {}
benediction['Nom'] = name
benediction['Classe'] = 'Oracle'
benediction['Niveau'] = 1
benediction['Auto'] = False
benediction['Description'] = cleanDescription(description)
benediction['Source'] = source
benediction['Référence'] = u
liste.append(benediction)
section = jumpTo(content, 'h2', {'class':'separator'}, 'Révélations')
if not section:
print('Aucune section "Révélations" trouvée!');
exit(1)
descr = ""
for el in section:
if el.name == "b":
benedictionName = cleanLabel(el.text)
benediction = {}
benediction['Nom'] = name + ": " + benedictionName
benediction['Classe'] = 'Oracle'
benediction['Niveau'] = 1
benediction['Auto'] = False
'Nom', 'Classe', 'Archétype', 'Prérequis', 'Source', 'Niveau', 'Auto',
'Description', 'Référence'
]
MATCH = ['Nom', 'Classe', 'Archétype']
liste = []
print("Extraction des aptitude (talents)...")
if MOCK_TALENT:
content = BeautifulSoup(open(MOCK_TALENT), features="lxml").body
else:
content = BeautifulSoup(urllib.request.urlopen(URL).read(),
features="lxml").body
section = jumpTo(content, 'h2', {'class': 'separator'},
u"Description des talents de roublard")
level = 0
for s in section:
if s.name == 'div' and s.has_attr(
'class') and "article_2col" in s['class']:
level = 2 if level == 0 else 10
talent = {'Source': 'MJ', 'Niveau': level}
newObj = False
brCount = 0
descr = ""
for e in s.children:
if e.name == 'h3':
if newObj:
exit(1)
return "MJ"
liste = []
listePouvoirs = []
print("Extraction des aptitude (lignages)...")
if MOCK_LIGNAGE:
content = BeautifulSoup(open(MOCK_LIGNAGE), features="lxml").body
else:
content = BeautifulSoup(urllib.request.urlopen(URL).read(),
features="lxml").body
section = jumpTo(content, 'h2', {'class': 'separator'},
"Les lignages d'ensorceleurs¶")
for s in section:
if s.name == "div" and "navmenu" in s.attrs['class']:
lignages = s.find_all("li")
for l in lignages:
link = l.find("a")
if link is None:
continue
lignage = {}
lignage['Nom'] = "Lignage: " + link.text
lignage['Classe'] = "Ensorceleur"
lignage['Source'] = extractSource(l.text)
lignage['Niveau'] = 1
lignage['Description'] = ""
link = data['Référence']
if data['Nom'] == "Duergar" or data['Nom'] == "Suli":
print("Ignore race %s saisie manuellement" % data['Nom'])
continue
print("Extraction des traits alternatifs de %s" % data['Nom'])
pageURL = link
if MOCK_RACE:
content = BeautifulSoup(open(MOCK_RACE),features="lxml").body
else:
content = BeautifulSoup(urllib.request.urlopen(pageURL).read(),features="lxml").body
# traits alternatifs
section = jumpTo(content, 'h2',{'class':'separator'}, u"Traits raciaux alternatifs")
for s in section:
if s.name == 'h2':
if not found:
print("Aucun trait racial alternatif trouvé!")
break; # avoid jumping to other sections
if s.name == 'div' and 'class' in s.attrs and "row" in s.attrs['class']:
for attr in s.find_all('li'):
descr = ""
remplaceText = ""
modifieText = ""
for el in attr.children:
if el.name == 'b':
name = el.text.strip()
if name.endswith('.'):
'Nom', 'Classe', 'Archétype', 'Prérequis', 'Source', 'Niveau', 'Auto',
'Description', 'Référence'
]
MATCH = ['Nom', 'Classe', 'Archétype']
liste = []
print("Extraction des aptitude (ordres)...")
if MOCK_ORDRE:
content = BeautifulSoup(open(MOCK_ORDRE), features="lxml").body
else:
content = BeautifulSoup(urllib.request.urlopen(URL).read(),
features="lxml").body
section = jumpTo(content, 'h2', {'class': 'separator'}, u"Ordres de chevalier")
ordre = {'Niveau': 1}
newObj = False
descr = ""
source = 'MJRA'
for el in section:
if el.name == "h2":
break
if el.name == "h3":
nom = cleanSectionName(el.text)
reference = URL + el.find_next("a")['href']
if newObj:
ordre['Classe'] = 'Chevalier'
URL = "http://www.pathfinder-fr.org/Wiki/Pathfinder-RPG.%c3%89tats%20pr%c3%a9judiciables.ashx"
MOCK_CF = None
#MOCK_CF = "mocks/conditions.html" # décommenter pour tester avec les conditions pré-téléchargées
FIELDS = ['Nom', 'Source', 'Description', 'Référence']
MATCH = ['Nom']
liste = []
if MOCK_CF:
content = BeautifulSoup(open(MOCK_CF), features="lxml").body
else:
content = BeautifulSoup(urllib.request.urlopen(URL).read(),
features="lxml").body
section = jumpTo(content, 'h2', {'class': 'separator'},
"Liste des états préjudiciables")
SOURCE = "MJ"
condition = {'Source': SOURCE}
newObj = False
advantage = False
descr = ""
for s in section:
if s.name == 'h2':
condition['Description'] = descr.strip()
liste.append(condition)
# avantages
SOURCE = "AM"
domain['Classe'] = "Prêtre"
domain['Source'] = "MJ"
domain['Niveau'] = 1
domain['Description'] = ""
domain['Référence'] = "http://www.pathfinder-fr.org/Wiki/" + link["href"]
print("Traitement: " + link["href"])
if MOCK_DOMAINE:
domainHTML = BeautifulSoup(open(MOCK_DOMAINE_PAGE),
features="lxml").body
else:
domainHTML = BeautifulSoup(urllib.request.urlopen(
domain['Référence']).read(),
features="lxml").body
pouvoirs = jumpTo(domainHTML, 'h2', {'class': 'separator'},
"Pouvoirs accordés")
if pouvoirs is None:
pouvoirs = jumpTo(domainHTML, 'b', {}, "Pouvoirs accordés")
if pouvoirs is None:
print("NOT FOUND!!")
continue
for p in pouvoirs:
if (p.name == 'h2'):
break
else:
domain['Description'] += html2text(p)
liste.append(domain)
#exit(1)
'Nom', 'Classe', 'Archétype', 'Prérequis', 'Source', 'Niveau', 'Auto',
'Description', 'Référence'
]
MATCH = ['Nom', 'Classe', 'Archétype']
liste = []
print("Extraction des aptitude (rages)...")
if MOCK_RAGE:
content = BeautifulSoup(open(MOCK_RAGE), features="lxml").body
else:
content = BeautifulSoup(urllib.request.urlopen(URL).read(),
features="lxml").body
section = jumpTo(content, 'h2', {'class': 'separator'},
u"Description des pouvoirs de rage")
source = None
sourceNext = None
for s in section:
if s.name == 'div':
rage = {'Source': 'MJ', 'Niveau': 1}
newObj = False
brCount = 0
descr = ""
for e in s.children:
if e.name == 'h3':
if newObj:
rage['Classe'] = 'Barbare'
rage['Description'] = descr.strip()
if not sourceNext is None:
# titre
name = content.find_next('h1', {'class': 'pagetitle'}).string.strip()
if name.startswith('Les '):
name = name[4:-1].title()
race['Nom'] = data['name']
# source
race['Source'] = data['source']
# référence
race['Référence'] = link
# traits
race['Traits'] = []
section = jumpTo(content, 'h2', {'class': 'separator'},
"Traits raciaux standards")
for s in section:
if s.name == 'div' and 'class' in s.attrs and "arrondi" in s.attrs[
'class']:
first = True
for attr in s.find_all('li'):
trait = {}
descr = ""
for el in attr.children:
if el.name == 'b':
name = el.text.strip()
if first:
trait['Nom'] = "Caractéristiques"
descr = name
else:
if name.endswith('.'):
if not ptsComp:
print("Points de compétence non-trouvé pour classe: %s" % name)
exit(1)
m = re.search('(\d) \\+ modificateur d[\'’]Intelligence', ptsComp)
if not m:
print("Points de compétence n'a pas pu être extrait!")
exit(1)
cl['RangsParNiveau'] = int(m.group(1))
# compétences de classe
cl['CompétencesDeClasse'] = []
sectionNames = ["Compétences de classe", "Compétences de la classe"]
section = None
for s in sectionNames:
section = jumpTo(content, 'h2', {'class': 'separator'}, s)
if section:
break
if not section:
print("- Compétences de la classe %s n'a pas être trouvée!!!" %
cl['Nom'])
continue
for s in section:
if s.name == 'a' and (len(s.text) > 3 or s.text.lower() == "vol"):
value = s.text
if value == u"Connaissances":
idx = s.next_sibling.index(')')
if idx > 0:
value += s.next_sibling[0:idx + 1].lower()