def parseJilinwula(content=""):
page = dict()
soup = getSoup(content)
if soup:
page['origin'] = origin
# 页面标题
page['title'] = title
# 初始化博客列表集合
blogs = list()
items = soup.find_all('div', 'item-label')
for item in items:
href = item.div.a['href']
_title = item.div.a.string
if _title:
blog = dict()
blog['id'] = href
blog['href'] = href
blog['title'] = _title
blog['publishTime'] = item.find_all(
'div', 'item-meta-date')[0].string.replace('发布于 ', '')
blogs.append(blog)
page['blogs'] = blogs
page['blogCount'] = len(blogs)
return page
def parseJmtaobao(content=""):
page = dict()
soup = getSoup(content)
if soup:
# 网页地址
page['origin'] = origin
# 页面标题
page['title'] = title
# 初始化博客列表集合
blogs = list()
# 最近的日志
articles = soup.find_all('article')
for article in articles:
blog = dict()
header = article.find('header')
blog['id'] = header.h1.a['href']
blog['href'] = origin + header.h1.a['href']
blog['title'] = header.h1.a.string.strip()
blog['publishTime'] = header.time.string.strip()
blogs.append(blog)
page['blogs'] = blogs
page['blogCount'] = len(blogs)
return page
def parseHchstudio(content=""):
page = dict()
soup = getSoup(content)
if soup:
# 网页地址
page['origin'] = origin
# 页面标题
page['title'] = title
# 初始化博客列表集合
blogs = list()
# 最近的日志
articles = soup.find_all('div', 'post')
for article in articles:
blog = dict()
blog['id'] = article.h1.a.string.strip()
blog['title'] = article.h1.a.string.strip()
blog['href'] = origin + article.h1.a['href']
blog['publishTime'] = article.find('span',
'post-meta').string.strip()
blog['author'] = article.find('a', id='authorH').string.strip()
blogs.append(blog)
page['blogs'] = blogs
page['blogCount'] = len(blogs)
return page