BeautifulSoup_lxml解析

def parseHtml(html):
    soup = BeautifulSoup(html, 'lxml')
    # print(soup.prettify)格式化输出
    # items = soup.find_all('div', attrs={'class': 'news-list-b'})
    # items = soup.select('Tag')#CSS选择器
    # items = soup.select('.class')属性
    # items = soup.select('#id')ID
    # items = soup.select('Tag[attr="属性值"]')标签+属性
    # items = soup.select('.class Tag #id')空格表示子节点，组合使用
    # items = soup.select('Tag').text取文本
    # items = soup.select('Tag').get_text()取文本
    # tag.get('className')取标签属性
    # tag['className']取标签属性
    # tag.attrs.get('className')取标签属性
    items = soup.select('.news-list-b .list .item .title a')
    for item in items:
        yield item.get('href')#attrs字典取属性

CSS选择器 子串匹配 模糊匹配

# soup = BeautifulSoup(html, 'lxml')
# trs = soup.select('#table_live tr[id*="tr1"]')
# id包含“tr1”字符串的tr标签
# soup.select('tag[attr="属性值"]') #标签+属性
# tags = soup.select('li[id^="newsLi"]') #标签+属性，id属性以newsLi开头
# tags = soup.select('li[id$="newsLi"]') #标签+属性，id属性以newsLi结尾
# tags = soup.select('li[id*="newsLi"]') #标签+属性，id属性包含newsLi

#div class=’content-list latest-content’
#div class=’content-list hot-content’

tags = soup.select('div.content-list.latest-content')