Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import pandas as pd
- import xml.etree.ElementTree as ET
- xml1 = """<?xml version="1.0" encoding="ISO-8859-1"?>
- <pisteAuditProfilingQualif>
- ...
- <demande>
- ...
- </demande>
- </pisteAuditProfilingQualif>"""
- xml2 = """<?xml version="1.0" encoding="ISO-8859-1"?>
- ...
- <demande>
- ...
- <REQ_TITLE_2>Sirrah!</REQ_TITLE_2>
- <REQ_NAME_2>George</REQ_NAME_2>
- </demande>
- </pisteAuditProfilingQualif>"""
- df = pd.DataFrame({'a':[42, 54],'xml':[xml1, xml2]})
- dfx = pd.DataFrame()
- for x in df.xml:
- ex = ET.fromstring(x)
- ed = ex.find('demande')
- dfx = dfx.append(dict([(e.tag, e.text) for e in ed.iter()]), ignore_index=True)
- print(df.join(dfx))
- a xml ... REQ_NAME_2 REQ_TITLE_2
- 0 42 <?xml version="1.0" encoding="ISO-8859-1"?>n ... ... NaN NaN
- 1 54 <?xml version="1.0" encoding="ISO-8859-1"?>n ... ... George Sirrah!
- [2 rows x 12 columns]
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement