1 def parseHtml(html):
 2     soup = BeautifulSoup(html, 'lxml')
 3     # print(soup.prettify)格式化输出
 4     # items = soup.find_all('div', attrs={'class': 'news-list-b'})
 5     # items = soup.select('Tag')#CSS选择器
 6     # items = soup.select('.class')属性
 7     # items = soup.select('#id')ID
 8     # items = soup.select('Tag[attr]')标签+属性
 9     # items = soup.select('.class Tag #id')空格表示子节点，组合使用
10     # items = soup.select('Tag').get_text()取文本
11     # tag.get('className')取标签属性
12     # tag['className']取标签属性
13     # tag.attrs.get('className')取标签属性
14     items = soup.select('.news-list-b .list .item .title a')
15     for item in items:
16         yield item.get('href')#attrs字典取属性