具有CSV内容的html标签<a>
的字符串值:
href = "data:text/csv;charset=UTF-8,%22csvcontentfollows"
是否可以通过标准模块(请求,lxml,纯python)的方法在没有此类元标头data:text/csv;charset=UTF-8
的情况下获取这样的CSV内容?
我不希望使用手动文本解析(通过regexp,index / startswith,split / partition)。
更新:
谢谢,我知道如何使用html。我对这种元标头的问题。我重新制定了。
答案 0 :(得分:1)
这是三种可能的解决方案。第一个使用本机Python的urllib.request.urlopen函数。第二个使用第三方库lxml。第二个使用本地html.parser模块中的HTMLParser类。第二和第三者使用第三方库来解析data URLs
的python-dataurihtml_string = """
<a href="data:text/csv;charset=UTF-8,%22csvcontentfollows">
<a href="data:text/csv;charset=UTF-8,%22csvcontentfollows">
<a href="data:text/csv;charset=UTF-8,%22csvcontentfollows">
"""
from contextlib import ExitStack
from urllib.request import urlopen
import lxml.etree
HREF = "href"
tree = lxml.etree.fromstring(html_string, lxml.etree.HTMLParser())
uris = (
item.attrib[HREF]
for item in tree.iterdescendants()
if HREF in item.attrib
)
with ExitStack() as stack:
resources = (stack.enter_context(urlopen(uri)) for uri in uris)
data = [fh.read().decode() for fh in resources]
print(data)
输出:
['csvcontentfollows', 'csvcontentfollows', 'csvcontentfollows']
import lxml.etree
from datauri import DataURI
tree = lxml.etree.fromstring(html_string, lxml.etree.HTMLParser())
HREF = "href"
uris = (
DataURI(item.attrib[HREF])
for item in tree.iterdescendants()
if HREF in item.attrib
)
attrs = ("mimetype", "charset", "is_base64", "data")
print([{attr: getattr(uri, attr) for attr in attrs}
for uri in uris])
输出:
[{'mimetype': 'text/csv', 'charset': 'UTF-8', 'is_base64': False, 'data': 'csvcontentfollows'}, {'mimetype': 'text/csv', 'charset': 'UTF-8', 'is_base64': False, 'data': 'csvcontentfollows'}, {'mimetype': 'text/csv', 'charset': 'UTF-8', 'is_base64': False, 'data': 'csvcontentfollows'}]
from html.parser import HTMLParser
from datauri import DataURI
uri_attrs = ("mimetype", "charset", "is_base64", "data")
class MyHTMLParser(HTMLParser):
def __init__(self):
super().__init__()
self.data = []
def handle_starttag(self, tag, attrs):
if tag == "a":
for attr, value in attrs:
if attr == "href":
for key, value in attrs:
uri = DataURI(value)
self.data.append({attr: getattr(uri, attr) for attr in uri_attrs})
parser = MyHTMLParser()
parser.feed(html_string)
print(parser.data)
输出:
[{'mimetype': 'text/csv', 'charset': 'UTF-8', 'is_base64': False, 'data': 'csvcontentfollows'}, {'mimetype': 'text/csv', 'charset': 'UTF-8', 'is_base64': False, 'data': 'csvcontentfollows'}, {'mimetype': 'text/csv', 'charset': 'UTF-8', 'is_base64': False, 'data': 'csvcontentfollows'}]