BeautifulSoup解析缺少闭合标签的html时,html.parser丢失数据只解析了第一条,lxml补全后没有丢失数据
from bs4 import BeautifulSoup
raw = """
<html>
<head>
<title>
test
</title>
</head>
<body>
<table>
<tbody>
<tr>
<td>
孙悟空
</td>
<td>
七十二变
</td>
<tr>
<td>
唐三藏
</td>
<td>
紧箍咒
</td>
</tbody>
</table>
</body>
</html>
"""
peoples = []
# html = BeautifulSoup(raw, "html.parser")
html = BeautifulSoup(raw, "lxml")
for row in html.select("table > tbody > tr"):
name, skill = "", ""
for i, col in enumerate(row.select("td")):
if i == 0:
name = col.text.strip()
elif i == 1:
skill = col.text.strip()
peoples.append({"name": name, "skill": skill})
print(peoples)