def Persons(self):
personlist = []
if self.imdbpage.find(text=re.compile("Directors?:")):
directors = self.imdbpage.find(text=re.compile("Directors?:")).parent.parent
directors = directors.findAll("a")
for person in directors:
if person.text.find("more credit") == -1:
personlist.append({"Name": person.text, "Type": "Director", "Role": ""})
if self.imdbpage.find("table", "cast_list"):
cast = self.imdbpage.find("table", "cast_list")
cast = cast.findAll("tr")
for person in cast:
name = tools.decode_htmlentities(
tools.remove_html_tags(str(person.find("td", "name"))).strip()
).replace("\n", " ")
role = tools.decode_htmlentities(
tools.remove_html_tags(str(person.find("td", "character"))).strip()
).replace("\n", " ")
name = re.sub("\s+", " ", name)
role = re.sub("\s+", " ", role)
if name != "None":
if role == "None":
role = ""
personlist.append({"Name": name, "Type": "Actor", "Role": role})
return personlist
def Persons(self):
personlist = []
if self.imdbpage.find(text=re.compile("Directors?:")):
directors = self.imdbpage.find(
text=re.compile("Directors?:")).parent.parent
directors = directors.findAll("a")
for person in directors:
if person.text.find('more credit') == -1:
personlist.append({
"Name": person.text,
"Type": "Director",
"Role": ""
})
if self.imdbpage.find("table", "cast_list"):
cast = self.imdbpage.find("table", "cast_list")
cast = cast.findAll('tr')
for person in cast:
name = tools.decode_htmlentities(
tools.remove_html_tags(str(person.find(
'td', 'name'))).strip()).replace("\n", " ")
role = tools.decode_htmlentities(
tools.remove_html_tags(str(person.find(
'td', 'character'))).strip()).replace("\n", " ")
name = re.sub('\s+', ' ', name)
role = re.sub('\s+', ' ', role)
if name != "None":
if role == "None": role = ""
personlist.append({
"Name": name,
"Type": "Actor",
"Role": role
})
return personlist
def Description(self):
page = self.imdbpage.find(id="overview-top")
if len(page.findAll("p")) == 2:
summary = str(page.findAll("p")[1])
removelink = re.compile(r"\<a.*\/a\>")
summary = removelink.sub("", summary)
summary = tools.remove_html_tags(summary)
summary = summary.replace("»", "")
summary = tools.decode_htmlentities(summary.decode("utf-8", "ignore"))
summary = summary.replace("\n", " ")
return summary
def Description(self):
page = self.imdbpage.find(id="overview-top")
if len(page.findAll('p')) == 2:
summary = str(page.findAll('p')[1])
removelink = re.compile(r'\<a.*\/a\>')
summary = removelink.sub('', summary)
summary = tools.remove_html_tags(summary)
summary = summary.replace('»', "")
summary = tools.decode_htmlentities(
summary.decode("utf-8", 'ignore'))
summary = summary.replace("\n", " ")
return summary
def ProductionYear(self):
movietitle = tools.decode_htmlentities(
tools.remove_html_tags(str(self.imdbpage.find('title'))).replace(
" - IMDb", ""))
movietitle = re.search("\(.*\)", movietitle).group(0).strip()
return re.search("[1-2][0-9]{3}", movietitle).group(0).strip()
def LocalTitle(self):
movietitle = tools.decode_htmlentities(
tools.remove_html_tags(str(self.imdbpage.find('title'))).replace(
" - IMDb", ""))
movietitle = re.sub("\(.*\)", "", movietitle).strip()
return movietitle
def IMDBrating(self):
return tools.remove_html_tags(
str(self.imdbpage.find(id="star-bar-user-rate").b))
def extract_clipping_content(raw):
m = re.search(r'<en-note>(.*)<\/en-note>', raw)
if m:
content = m.groups()[0]
if content:
return tools.remove_html_tags(content)
def extract_clipping_content(raw):
m = re.search(r'<en-note>(.*)<\/en-note>', raw)
if m:
content = m.groups()[0]
if content:
return tools.remove_html_tags(content)
def ProductionYear(self):
movietitle = tools.decode_htmlentities(
tools.remove_html_tags(str(self.imdbpage.find("title"))).replace(" - IMDb", "")
)
movietitle = re.search("\(.*\)", movietitle).group(0).strip()
return re.search("[1-2][0-9]{3}", movietitle).group(0).strip()
def LocalTitle(self):
movietitle = tools.decode_htmlentities(
tools.remove_html_tags(str(self.imdbpage.find("title"))).replace(" - IMDb", "")
)
movietitle = re.sub("\(.*\)", "", movietitle).strip()
return movietitle
def IMDBrating(self):
return tools.remove_html_tags(str(self.imdbpage.find(id="star-bar-user-rate").b))
