BeautifulSoup 用法记录

soup = BeautifulSoup(html_content, 'html.parser')

### 查找指定class的table
labels = soup.find_all("table", class_="cls_name")


### 查找指定id的table
label = soup.find("table", id_="cls_id")

### 正则匹配指定的url
links = table.find_all("a", href=re.compile(r"/[0-9]+\.html"))

### 获取标签的纯文本
text = label.text
text = label.get_text()