def _gnewsItem2Page(item):
pageItem = {}
pageItem["title"] = htmlutil.getTextContent(item.get("title"))
pageItem["url"] = item.get("unescapedUrl")
pageItem["content"] = htmlutil.getTextContent(item.get("content"))
pageItem["publisher"] = item.get("publisher")
pageItem["published"] = dateutil.jsDate2utc14(item.get("publishedDate"))
if item.get("image"):
img = {}
img["url"] = item["image"].get("url")
img["width"] = item["image"].get("tbWidth")
img["height"] = item["image"].get("tbHeight")
pageItem["img"] = img
return pageItem
def getItemFromScript(element):
if element.tag != 'a':
return None
url = element.get('href')
title = lxmlutil.getScriptConstantString(element)
if title:
title = htmlutil.getTextContent(title)
item = {}
if url:
item['url'] = url
if title:
item['title'] = title
return item
def getItemFromScript(element):
if element.tag != "a":
return None
url = element.get("href")
title = lxmlutil.getScriptConstantString(element)
if title:
title = htmlutil.getTextContent(title)
item = {}
if url:
item["url"] = url
if title:
item["title"] = title
return item
def _googleItem2page(item):
pageItem = {}
pageItem['title'] = htmlutil.getTextContent(item.get('title'))
pageItem['url'] = item.get('unescapedUrl')
pageItem['content'] = htmlutil.getTextContent(item.get('content'))
return pageItem