def extract_content(self, param, clean=None, before=None, after=None):
params = {"params": {"selector": "div#eData > dl"}, "method": "select"}
img_params = {
"params": {
"selector": "dd:nth-of-type(1)"
},
"method": "select"
}
text_params = {
"params": {
"selector": "dd:nth-of-type(5)"
},
"method": "select"
}
dls = find_tags(self._soup, params)
content = list()
for dl in dls:
image_tag = find_tag(dl, img_params)
if not image_tag:
continue
url = extract_tag_attribute(image_tag, "text")
if not (url and url.startswith("http") and url.endswith(".jpg")):
continue
content.append({"tag": "img", "src": url})
text_tag = find_tag(dl, text_params)
if not text_tag:
continue
text = extract_tag_attribute(text_tag, "text")
if not text:
continue
text = text.replace("<br />", " ").strip()
content.append({"tag": "p", "text": text})
return self.clean_content(content)
def extract_content(self, param, clean=None, before=None, after=None):
roots = list()
if param is None:
roots.append(self._find_content_tag())
elif isinstance(param, list):
for p in param:
root = find_tag(self._soup, p)
if root is None or root in roots:
continue
else:
roots.append(root)
else:
roots.append(find_tag(self._soup, param))
content = list()
for root in roots:
if root is None:
continue
if before is not None:
self._clean_content_before(root, before)
if after is not None:
self._clean_content_after(root, after)
if clean is not None:
self._clean_content(root, clean)
if root.name == "textarea":
content.extend(self.parse_text_area(root))
else:
content.extend(self.parse_content(root))
return self.clean_content(content)
def judge_missing(self, param):
if param is None:
return False
if isinstance(param, list):
for p in param:
if find_tag(self.soup, p):
return True
else:
if find_tag(self.soup, param):
return True
return False
def _clean_content_after(self, root, param):
tag = find_tag(root, param)
if tag is not None:
siblings = []
for sibling in tag.next_siblings:
siblings.append(sibling)
for sibling in siblings:
sibling.extract()
tag.extract()
def _clean_content_before(self, root, param):
tag = find_tag(root, param)
if tag is not None:
siblings = []
for sibling in tag.previous_siblings:
siblings.append(sibling)
for sibling in siblings:
sibling.extract()
tag.extract()
def clean_author(self, author):
param = {
"method": "select",
"params": {
"selector": "div#news_template_03_AuthorAndTime > span"
}
}
tag = find_tag(root=self.soup, param=param)
text = extract_tag_attribute(root=tag)
return author.replace(text, "")
def _extract_tag(root, param):
"""
param = {
"method": "find_all",
"params": {},
"nth": 0,
"attribute": "text",
}
:param root:
:type root:
:param param:
:type param:
:return:
:rtype:
"""
tag = find_tag(root, param)
attribute = param.get("attribute")
if attribute is None:
string = extract_tag_attribute(tag, "text")
else:
string = extract_tag_attribute(tag, attribute)
return string
def find_tag_extract_attribute(root, params):
tag = find_tag(root, params)
if not tag:
return None
return extract_tag_attribute(tag, params.get("attribute", "text"))