def get_body(self):
try :
element_body = self.get_element_body()
except NoneMainDiv:
return None
else:
div_header_element = self.parser.select(element_body, "div.header", 1)
element_detail = self.parser.select(element_body, "div.details", 1)
div_content_element = self.parser.select(element_body, "div.content", 1)
drop_comments(element_body)
try_remove(self.parser, element_body, "div.sidebar")
try_remove(self.parser, element_detail, "div.footer")
try_remove_from_selector_list(self.parser,
div_header_element,
["h1", "div.picture", "div.date",
"div.news-single-img",
"div.metas_img", "strong"])
try_remove_from_selector_list(self.parser,
div_content_element,
["div.tw_button", "div.wpfblike"])
try :
description_element = self.parser.select(div_header_element,
"div.description", 1)
except BrokenPageError:
pass
else:
text_content = description_element.text_content()
if len(text_content.strip()) == 0 :
description_element.drop_tree()
else:
if len(description_element) == 1:
description_element.drop_tag()
if len(div_header_element.text_content().strip()) == 0:
div_header_element.drop_tree()
if len(div_header_element) == 1:
div_header_element.drop_tag()
if len(element_detail) == 1:
element_detail.drop_tag()
div_content_element.drop_tag()
return self.parser.tostring(element_body)
def get_body(self):
try:
element_body = self.get_element_body()
except NoneMainDiv:
return None
else:
div_header_element = self.parser.select(element_body, "div.header",
1)
element_detail = self.parser.select(element_body, "div.details", 1)
div_content_element = self.parser.select(element_body,
"div.content", 1)
drop_comments(element_body)
try_remove(self.parser, element_body, "div.sidebar")
try_remove(self.parser, element_detail, "div.footer")
try_remove_from_selector_list(self.parser, div_header_element, [
"h1", "div.picture", "div.date", "div.news-single-img",
"div.metas_img", "strong"
])
try_remove_from_selector_list(self.parser, div_content_element,
["div.tw_button", "div.wpfblike"])
try:
description_element = self.parser.select(
div_header_element, "div.description", 1)
except BrokenPageError:
pass
else:
text_content = description_element.text_content()
if len(text_content.strip()) == 0:
description_element.drop_tree()
else:
if len(description_element) == 1:
description_element.drop_tag()
if len(div_header_element.text_content().strip()) == 0:
div_header_element.drop_tree()
if len(div_header_element) == 1:
div_header_element.drop_tag()
if len(element_detail) == 1:
element_detail.drop_tag()
div_content_element.drop_tag()
return self.parser.tostring(element_body)
def get_body(self):
element_body = self.get_element_body()
remove_from_selector_list(self.parser, element_body,
[self.element_title_selector])
drop_comments(element_body)
try_drop_tree(self.parser, element_body, "script")
try_drop_tree(self.parser, element_body, "liste")
try_remove_from_selector_list(self.parser, element_body, [
"div#article-comments", "div.infos", "div.photo",
"div.art_bandeau_bottom", "div.view", "span.auteur_long",
"#toolsbar", 'link'
])
for image in self.parser.select(element_body, 'img'):
if image.attrib['src'].endswith('coeur-.gif'):
image.drop_tree()
for div in self.parser.select(element_body, 'div'):
if div.text == ' Player Figaro BFM ':
obj = div.getnext()
a = obj.getnext()
if obj.tag == 'object':
obj.drop_tree()
if a.tag == 'a' and 'BFM' in a.text:
a.drop_tree()
div.drop_tree()
# This part of the article seems manually generated.
for crappy_title in self.parser.select(element_body, 'p strong'):
if crappy_title.text == 'LIRE AUSSI :' or crappy_title.text == 'LIRE AUSSI:':
# Remove if it has only links
for related in crappy_title.getparent().itersiblings(tag='p'):
if len(related) == len(list(
related.iterchildren(tag='a'))):
related.drop_tree()
else:
break
crappy_title.drop_tree()
txts = element_body.find_class("texte")
if len(txts) > 0:
txts[0].drop_tag()
element_body.tag = "div"
return self.parser.tostring(element_body)
def get_body(self):
element_body = self.get_element_body()
remove_from_selector_list(self.parser, element_body, [self.element_title_selector])
drop_comments(element_body)
try_drop_tree(self.parser, element_body, "script")
try_drop_tree(self.parser, element_body, "liste")
try_remove_from_selector_list(self.parser, element_body, ["div#article-comments", "div.infos", "div.photo", "div.art_bandeau_bottom", "div.view", "span.auteur_long", "#toolsbar", 'link'])
for image in self.parser.select(element_body, 'img'):
if image.attrib['src'].endswith('coeur-.gif'):
image.drop_tree()
for div in self.parser.select(element_body, 'div'):
if div.text == ' Player Figaro BFM ':
obj = div.getnext()
a = obj.getnext()
if obj.tag == 'object':
obj.drop_tree()
if a.tag == 'a' and 'BFM' in a.text:
a.drop_tree()
div.drop_tree()
# This part of the article seems manually generated.
for crappy_title in self.parser.select(element_body, 'p strong'):
if crappy_title.text == 'LIRE AUSSI :' or crappy_title.text == 'LIRE AUSSI:':
# Remove if it has only links
for related in crappy_title.getparent().itersiblings(tag='p'):
if len(related) == len(list(related.iterchildren(tag='a'))):
related.drop_tree()
else:
break
crappy_title.drop_tree()
txts = element_body.find_class("texte")
if len(txts) > 0:
txts[0].drop_tag()
element_body.tag = "div"
return self.parser.tostring(element_body)
