def parse(html,keywords,url_prefix):
soup = BeautifulSoup(html,'html.parser');
header_list = soup.find_all('header',attrs={'class':'entry-header'});
results= {}
for header in header_list:
for child in header.descendants:
if child.name=='a' and base_parser.isContainKeyword(keywords,child.text):
if not base_parser.isContainKeyword('tags',child['href']):
#titles
results[child.text] = url_prefix + child['href']
else:
#tags
results[header.find('a').text] = url_prefix + header.find('a')['href']
return results
def parse(html, keywords, url_prefix):
soup = BeautifulSoup(html, 'html.parser')
header_list = soup.find_all('header', attrs={'class': 'entry-header'})
results = {}
for header in header_list:
for child in header.descendants:
if child.name == 'a' and base_parser.isContainKeyword(
keywords, child.text):
if not base_parser.isContainKeyword('tags', child['href']):
#titles
results[child.text] = url_prefix + child['href']
else:
#tags
results[header.find(
'a').text] = url_prefix + header.find('a')['href']
return results
def parse(html,keywords,url_prefix):
soup=BeautifulSoup(html,'html.parser')
results= {}
title_list = soup.find_all('td',attrs={'class':'title'})
for title in title_list:
a = title.find('a');
if a is not None and base_parser.isContainKeyword(keywords,a.text) and a['href'].startswith('http'):
results[a.text] = a['href']
return results
def parse(html, keywords, url_prefix):
soup = BeautifulSoup(html, "html.parser")
news_blocks = soup.find_all("div", class_="news_type_block")
results = {}
for block in news_blocks:
h2_block = block.contents[1]
title_block = h2_block.contents[1]
if base_parser.isContainKeyword(keywords, title_block.text):
results[base_parser.simplify_text(title_block.text)] = base_parser.get_url(
url_prefix, title_block["href"], "/news"
)
return results
def parse(html, keywords, url_prefix):
soup = BeautifulSoup(html, 'html.parser')
news_blocks = soup.find_all('div', class_='news_type_block')
results = {}
for block in news_blocks:
h2_block = block.contents[1]
title_block = h2_block.contents[1]
if base_parser.isContainKeyword(keywords, title_block.text):
results[base_parser.simplify_text(
title_block.text)] = base_parser.get_url(
url_prefix, title_block['href'], '/news')
return results
