def parse(publishedFormat, titleElement, mainElement):
if titleElement.sourceline >= mainElement.sourceline:
return None
publishedResult = None
element = lxmlutil.getFullNext(titleElement)
while element.sourceline < mainElement.sourceline:
publishedResult = _getPublishedInside(publishedFormat, element)
if publishedResult:
break
element = lxmlutil.getFullNext(element)
return publishedResult
def _getNextText(element):
while element is not None:
if lxmlutil.isVisibleElement(element) and element.text:
return element.text.strip()
elif element.tail:
return element.tail.strip()
element = lxmlutil.getFullNext(element)
return None
def parse(url, contentElement, titleElement, mainElement):
startLine = titleElement.sourceline
mainNext = lxmlutil.getFullNext(mainElement)
if mainNext is None:
endLine = -1
else:
endLine = mainNext.sourceline
items = pyquery.PyQuery(contentElement)('img')
result = []
for item in items:
if item.sourceline < startLine:
continue
if endLine > 0 and item.sourceline > endLine:
break
img = _parseImg(url, item)
if img:
result.append(img)
return result
