我有一个看起来像来自API的xml。
import requests
import pandas as pd
import lxml.etree as et
from lxml import etree
url = 'abc.com'
xml_data1 = requests.get(url).content
print(xml_data1)
xml_data1：
<?xml version="1.0" encoding="utf-8"?>
<Leads>
<Lead Id="123" LeadTitle="test, test., , (123) 456-7890, " CreateDate="01/01/2017 11:11:11" ModifyDate="01/04/2017 03:03:03" ACount="1" LCount="4" RCount="0" ROnly="false" Flagged="false" LastDistributionDate="01/01/2017 10:10:10" LeadFormType="test test">
<Campaign CampaignId="123" CampaignTitle="abc" />
<Status StatusId="123" StatusTitle="test" />
<Agent AgentId="123" AgentName="test, test" AgentEmail="a@a.com">
<AgentCustomFields custom1="test test, test" custom2="test" custom3="" custom4="" />
</Agent>
<Fields>
<Field FieldId="7" Value="a@a.com" FieldTitle="test" FieldType="test" />
<Field FieldId="8" Value="test" FieldTitle="test 1" FieldType="test" />
<Field FieldId="9" Value="test" FieldTitle="City" FieldType="Text" />
<Field FieldId="10" Value="test" FieldTitle="State" FieldType="State" />
<Field FieldId="11" Value="test" FieldTitle="test" FieldType="Zip" />
<Field FieldId="950" Value="test." FieldTitle="Business Name" FieldType="Text" />
<Field FieldId="1261" Value="Intuit Desktop" FieldTitle="test" FieldType="Text" />
<Field FieldId="1262" Value="test" FieldTitle="test" FieldType="Text" />
<Field FieldId="1263" Value="test" FieldTitle="test" FieldType="Number" />
<Field FieldId="1267" Value="test" FieldTitle="test" FieldType="Text" />
<Field FieldId="1310" Value="test" FieldTitle="test" FieldType="Phone" />
<Field FieldId="1319" Value="test" FieldTitle="test" FieldType="Number" />
<Field FieldId="1485" Value="test" FieldTitle="tst" FieldType="State" />
</Fields>
<Logs>
<StatusLog>
<Status LogId="123" LogDate="01/04/2017 03:08:44" StatusId="28" StatusTitle="test" AgentId="19" AgentName="test" AgentEmail="test@test.com" />
</StatusLog>
<ActionLog>
<Action LogId="123" ActionTypeId="73" ActionTypeName="test" MilestoneId="1" ActionDate="01/04/2017 03:08:44" ActionNote="test" AgentId="19" AgentName="test,test" AgentEmail="test@test.com" />
</ActionLog>
<EmailLog>
<Email LogId="123" SendDate="01/01/2017 20:53:39" EmailTemplateId="1" EmailTemplateName="test " AgentId="1" AgentName="test" AgentEmail="test@test.com" />
</EmailLog>
<DistributionLog>
<Distribution LogId="1" LogDate="01/01/2017 10:10:08" DistributionProgramId="1" DistributionProgramName="test" AssignedAgentId="1" AssignedAgentName="test,test" AssignedAgentEmail="test@test.com" />
</DistributionLog>
<CreationLog LogId="1" LogDate="01/01/2017 10:10:05" Imported="true" CreatedByAgentId="1" CreatedByAgentName="test, test" CreatedByAgentEmail="test@test.com" />
</Logs>
</Lead>
</Leads>
您有工作上的顾虑吗，我无法发布整个xml字符串，但是它遵循上面的结构。根据xml验证程序，xml是正确的，但是当我进行另一个API调用并返回另一个xml字符串时，它看起来像这样：
<?xml version="1.0" encoding="utf-8"?>\r\n<Leads>\r\n <Lead Id="123" />\r\n <Lead Id="456" />\r\n</Leads>'
我可以使用以下代码将上述xml成功传递到数据框：
class XML2DataFrame:
def __init__(self, xml_data):
self.root = ET.XML(xml_data)
def parse_root(self, root):
"""Return a list of dictionaries from the text
and attributes of the children under this XML root."""
return [self.parse_element(child) for child in iter(root)]
def parse_element(self, element, parsed=None):
""" Collect {key:attribute} and {tag:text} from thie XML
element and all its children into a single dictionary of strings."""
if parsed is None:
parsed = dict()
for key in element.keys():
if key not in parsed:
parsed[key] = element.attrib.get(key)
else:
raise ValueError('duplicate attribute {0} at element {1}'.format(key, element.getroottree().getpath(element)))
""" Apply recursion"""
for child in list(element):
self.parse_element(child, parsed)
return parsed
def process_data(self):
""" Initiate the root XML, parse it, and return a dataframe"""
structure_data = self.parse_root(self.root)
return pd.DataFrame(structure_data)
xml2df = XML2DataFrame(xml_data)
xml_dataframe = xml2df.process_data()
但是，当我将可能格式错误的xml字符串传递给上述函数时，会出现错误：
AttributeError: 'xml.etree.ElementTree.Element' object has no attribute 'getroottree'
由于可能格式错误的xml在同一个标记中具有多个值，因此我认为该函数无法对其进行解析。
我希望将可能格式错误的xml推送到平面数据框中。
从xml编辑输出行列标题：
ActionCount CreateDate Flagged Id LastDistributionDate LeadFormType LeadTitle LogCount FieldId FieldTitle FieldType Value CampaignId CampaignTitle AgentEmail AgentId AgentName LogDate LogId StatusId StatusTitle AssignedAgentEmail AssignedAgentId AssignedAgentName DistributionProgramId DistributionProgramName LogDate LogId
答案 0 :(得分：2)
自从您更新了问题，我决定用新的xml发布另一个答案。
from bs4 import BeautifulSoup
import pandas as pd
xml = """
<?xml version="1.0" encoding="utf-8"?>
<Leads>
<Lead Id="123" LeadTitle="test, test., , (123) 456-7890, " CreateDate="01/01/2017 11:11:11" ModifyDate="01/04/2017 03:03:03" ACount="1" LCount="4" RCount="0" ROnly="false" Flagged="false" LastDistributionDate="01/01/2017 10:10:10" LeadFormType="test test">
<Campaign CampaignId="123" CampaignTitle="abc" />
<Status StatusId="123" StatusTitle="test" />
<Agent AgentId="123" AgentName="test, test" AgentEmail="a@a.com">
<AgentCustomFields custom1="test test, test" custom2="test" custom3="" custom4="" />
</Agent>
<Fields>
<Field FieldId="7" Value="a@a.com" FieldTitle="test" FieldType="test" />
<Field FieldId="8" Value="test" FieldTitle="test 1" FieldType="test" />
<Field FieldId="9" Value="test" FieldTitle="City" FieldType="Text" />
<Field FieldId="10" Value="test" FieldTitle="State" FieldType="State" />
<Field FieldId="11" Value="test" FieldTitle="test" FieldType="Zip" />
<Field FieldId="950" Value="test." FieldTitle="Business Name" FieldType="Text" />
<Field FieldId="1261" Value="Intuit Desktop" FieldTitle="test" FieldType="Text" />
<Field FieldId="1262" Value="test" FieldTitle="test" FieldType="Text" />
<Field FieldId="1263" Value="test" FieldTitle="test" FieldType="Number" />
<Field FieldId="1267" Value="test" FieldTitle="test" FieldType="Text" />
<Field FieldId="1310" Value="test" FieldTitle="test" FieldType="Phone" />
<Field FieldId="1319" Value="test" FieldTitle="test" FieldType="Number" />
<Field FieldId="1485" Value="test" FieldTitle="tst" FieldType="State" />
</Fields>
<Logs>
<StatusLog>
<Status LogId="123" LogDate="01/04/2017 03:08:44" StatusId="28" StatusTitle="test" AgentId="19" AgentName="test" AgentEmail="test@test.com" />
</StatusLog>
<ActionLog>
<Action LogId="123" ActionTypeId="73" ActionTypeName="test" MilestoneId="1" ActionDate="01/04/2017 03:08:44" ActionNote="test" AgentId="19" AgentName="test,test" AgentEmail="test@test.com" />
</ActionLog>
<EmailLog>
<Email LogId="123" SendDate="01/01/2017 20:53:39" EmailTemplateId="1" EmailTemplateName="test " AgentId="1" AgentName="test" AgentEmail="test@test.com" />
</EmailLog>
<DistributionLog>
<Distribution LogId="1" LogDate="01/01/2017 10:10:08" DistributionProgramId="1" DistributionProgramName="test" AssignedAgentId="1" AssignedAgentName="test,test" AssignedAgentEmail="test@test.com" />
</DistributionLog>
<CreationLog LogId="1" LogDate="01/01/2017 10:10:05" Imported="true" CreatedByAgentId="1" CreatedByAgentName="test, test" CreatedByAgentEmail="test@test.com" />
</Logs>
</Lead>
</Leads>
"""
soup = BeautifulSoup(xml, "xml")
# Get Attributes from all nodes
attrs = []
for elm in soup(): # soup() is equivalent to soup.find_all()
attrs.append(elm.attrs)
# Since you want the data in a dataframe, it makes sense for each field to be a new row consisting of all the other node attributes
fields_attribute_list= [x for x in attrs if 'FieldId' in x.keys()]
other_attribute_list = [x for x in attrs if 'FieldId' not in x.keys() and x != {}]
# Make a single dictionary with the attributes of all nodes except for the `Field` nodes.
attribute_dict = {}
for d in other_attribute_list:
for k, v in d.items():
attribute_dict.setdefault(k, v)
# Update each field row with attributes from all other nodes.
full_list = []
for field in fields_attribute_list:
field.update(attribute_dict)
full_list.append(field)
# Make Dataframe
df = pd.DataFrame(full_list)
但是，请注意，此方法会覆盖xml中具有相同名称的属性ID，例如LogId。无论如何，这段代码应该可以帮助您入门。
答案 1 :(得分：1)
我认为您会发现BeautifulSoup进行XML / HTML解析要容易得多。它还很好地处理了格式错误的XML和HTML。
pip install beautifulsoup4
以下是如何解析BeautifulSoup提供的xml。
from bs4 import BeautifulSoup
import pandas as pd
xml = """
<?xml version="1.0" encoding="utf-8"?>
<Leads>
<Lead Id="123" LeadTitle="test, test., , (123) 456-7890, " CreateDate="01/01/2017 11:11:11" ModifyDate="01/04/2017 03:03:03" ACount="1" LCount="4" RCount="0" ROnly="false" Flagged="false" LastDistributionDate="01/01/2017 10:10:10" LeadFormType="test test"></Lead>
<Lead Id="123" />
<Lead Id="456" />
</Leads>
"""
soup = BeautifulSoup(xml, "xml")
leads = soup.findAll('Lead')
lead_list = []
for lead in leads:
lead_list.append(lead.attrs)
df = pd.DataFrame(lead_list)
df
输出：
ACount CreateDate Flagged Id LCount LastDistributionDate LeadFormType LeadTitle ModifyDate RCount ROnly
0 1 01/01/2017 11:11:11 false 123 4 01/01/2017 10:10:10 test test test, test., , (123) 456-7890, 01/04/2017 03:03:03 0 false
1 NaN NaN NaN 123 NaN NaN NaN NaN NaN NaN NaN
2 NaN NaN NaN 456 NaN NaN NaN NaN NaN NaN NaN