diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2018-04-04 11:47:41 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2018-04-04 11:47:41 -0700 |
| commit | e8eb959fbdd5d13cd53421ddf2487811d049c4e8 (patch) | |
| tree | fbc8c052aac7d4eeb83da0a2d181fb585d2e4a8b /extraction/xml2json.py | |
| parent | 7056c83d4a6bc107155eedb1b39f38dc6d290a39 (diff) | |
| download | sandcrawler-e8eb959fbdd5d13cd53421ddf2487811d049c4e8.tar.gz sandcrawler-e8eb959fbdd5d13cd53421ddf2487811d049c4e8.zip | |
more WIP on extractor
Diffstat (limited to 'extraction/xml2json.py')
| -rw-r--r-- | extraction/xml2json.py | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/extraction/xml2json.py b/extraction/xml2json.py new file mode 100644 index 0000000..f956014 --- /dev/null +++ b/extraction/xml2json.py @@ -0,0 +1,8 @@ + +import json +import sys +import xmltodict + +with open('tests/files/23b29ea36382680716be08fc71aa81bd226e8a85.xml', 'rb') as f: + thing = xmltodict.parse(f, process_namespaces=False) + print(json.dumps(thing)) |