def add_item_atoz(soup, provider, count): #Scrape items from an AtoZ-style HTML page
baseurl = base_url(provider)
info = tools.defaultinfo()
info["Studio"] = provider
if soup.find('h5'):
link = soup.h5.find("a", attrs={"href": re.compile(baseurl)})
if link:
infoitems = {}
href = re.match("%s/(.*?)/%s/([0-9]+)/%s/([0-9]+)/%s/([0-9]+)/" % (baseurl, tv3_urls["VIDEO1"], tv3_urls["VIDEO2"], tv3_urls["VIDEO3"]), link['href'])
if href:
if link.string:
title = link.string.strip()
if title <> "":
info["TVShowTitle"] = title
image = soup.find("img", attrs={"src": re.compile(tv3_urls["IMG_RE2"]), "title": True})
if image:
info.update(tools.imageinfo(image))
info.update(seasonepisode(soup.contents[4]))
info["Title"] = tools.itemtitle(info["TVShowTitle"], info["PlotOutline"])
plot = soup.find("span", attrs={"class": "lite"})
if plot.string:
cleanedplot = plot.string.strip()
if cleanedplot:
info["Plot"] = tools.unescape(cleanedplot)
info["Count"] = count
info["FileName"] = "%s?ch=TV3&id=%s&info=%s" % (sys.argv[0], "%s,%s,%s,%s" % (href.group(1), href.group(2), href.group(3), href.group(4)), urllib.quote(str(info)))
infoitems[info["Title"]] = info
#tools.addlistitem(int(sys.argv[1]), info, tv3_urls["Fanart"], 0)
tools.addlistitems(infoitems, tv3_urls["Fanart"], 0)
def add_item_show(soup, provider, count, title): #Scrape items from a show-style HTML page
info = tools.defaultinfo()
info["Studio"] = provider
bold = soup.find('b')
if bold:
link = bold.find("a", attrs={"href": re.compile(tv3_urls["FEEDBURNER_RE"])})
if link:
urltype = "other"
else:
link = bold.find("a", attrs={"href": re.compile(base_url("tv3"))})
if link:
urltype = "tv3"
if link:
if link.string:
plot = link.string.strip()
if plot <> "":
info["PlotOutline"] = plot
info["TVShowTitle"] = title
image = soup.find("img", attrs={"src": re.compile(tv3_urls["IMG_RE"])})
if image:
info.update(tools.imageinfo(image))
info.update(seasonepisode(link))
info["Title"] = tools.itemtitle(info["TVShowTitle"], info["PlotOutline"])
info["Count"] = count
if urltype == "tv3":
href = re.search("%s/(.*?)/%s/([0-9]+)/%s/([0-9]+)/%s/([0-9]+)/" % (base_url("tv3"), tv3_urls["VIDEO1"], tv3_urls["VIDEO2"], tv3_urls["VIDEO3"]), link['href'])
if href:
info["FileName"] = "%s?ch=TV3&id=%s&info=%s" % (sys.argv[0], "%s,%s,%s,%s" % (href.group(1), href.group(2), href.group(3), href.group(4)), urllib.quote(str(info)))
elif urltype == "other":
info["FileName"] = "%s?ch=TV3&id=%s&info=%s" % (sys.argv[0], urllib.quote(link["href"]), urllib.quote(str(info)))
tools.addlistitem(int(sys.argv[1]), info, tv3_urls["Fanart"], 0)
def add_item_div(soup, provider, count): #Scrape items from a div-style HTML page
baseurl = base_url(provider)
info = tools.defaultinfo()
info["Studio"] = provider
sys.stderr.write(baseurl)
link = soup.find("a", attrs={"href": re.compile(baseurl)})
if link:
href = re.match("%s/(.*?)/%s/([0-9]+)/%s/([0-9]+)/%s/([0-9]+)/" % (baseurl, tv3_urls["VIDEO1"], tv3_urls["VIDEO2"], tv3_urls["VIDEO3"]), link['href'])
if href:
if link.string:
title = link.string.strip()
if title <> "":
info["TVShowTitle"] = title
image = soup.find("img", attrs={"src": re.compile(tv3_urls["IMG_RE"]), "title": True})
if image:
info.update(tools.imageinfo(image))
se = soup.find("span", attrs={"class": "title"})
if se:
info.update(seasonepisode(se))
date = soup.find("span", attrs={"class": "dateAdded"})
if date:
info.update(dateduration(date))
info["Title"] = tools.itemtitle(info["TVShowTitle"], info["PlotOutline"])
info["Count"] = count
plot = soup.find("div", attrs={"class": "left"}).string
if plot:
if plot.strip() <> "":
info["Plot"] = tools.unescape(plot.strip())
info["FileName"] = "%s?ch=TV3&id=%s&info=%s" % (sys.argv[0], "%s,%s,%s,%s" % (href.group(1), href.group(2), href.group(3), href.group(4)), urllib.quote(str(info)))
tools.addlistitem(int(sys.argv[1]), info, tv3_urls["Fanart"], 0)
def add_item_table(soup, provider, count, title): #Scrape items from a table-style HTML page
info = tools.defaultinfo()
info["Studio"] = provider
link = soup.find('a')
if link:
if link.string:
plot = link.string.strip()
if plot <> "":
info["PlotOutline"] = plot
info["TVShowTitle"] = title
info.update(seasonepisode(link))
info["Title"] = tools.itemtitle(info["TVShowTitle"], info["PlotOutline"])
info["Count"] = count
href = re.search("%s/(.*?)/%s/([0-9]+)/%s/([0-9]+)/%s/([0-9]+)/" % (base_url("tv3"), tv3_urls["VIDEO1"], tv3_urls["VIDEO2"], tv3_urls["VIDEO3"]), link['href'])
if href:
info["FileName"] = "%s?ch=TV3&id=%s&info=%s" % (sys.argv[0], "%s,%s,%s,%s" % (href.group(1), href.group(2), href.group(3), href.group(4)), urllib.quote(str(info)))
tools.addlistitem(int(sys.argv[1]), info, tv3_urls["Fanart"], 0)
def add_item_search(soup, provider, count): #Scrape items from a table-style HTML page
baseurl = base_url(provider)
info = tools.defaultinfo()
info["Studio"] = provider
title = soup.find("div", attrs={"class": 'catTitle'})
if title:
info["TVShowTitle"] = title.a.string.strip()
href = re.match("%s/(.*?)/%s/([0-9]+)/%s/([0-9]+)/%s/([0-9]+)/" % (baseurl, tv3_urls["VIDEO1"], tv3_urls["VIDEO2"], tv3_urls["VIDEO3"]), title.a['href'])
image = soup.find("img")
if image:
info.update(tools.imageinfo(image))
ep = soup.find("div", attrs={"class": 'epTitle'})
if ep:
if ep.a:
info.update(seasonepisode(ep.a))
date = soup.find("div", attrs={"class": 'epDate'})
# if date:
# sys.stderr.write(date.span[1].string.strip())
info["Title"] = tools.itemtitle(info["TVShowTitle"], info["PlotOutline"])
info["Count"] = count
info["FileName"] = "%s?ch=TV3&id=%s&info=%s" % (sys.argv[0], "%s,%s,%s,%s" % (href.group(1), href.group(2), href.group(3), href.group(4)), urllib.quote(str(info)))
tools.addlistitem(int(sys.argv[1]), info, tv3_urls["Fanart"], 0)
