diff options
author | Bryan Newbold <bnewbold@archive.org> | 2020-10-30 17:33:37 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2020-10-30 17:33:37 -0700 |
commit | cefbc6fa46e6586d8735f40b3b5432a759edd5f1 (patch) | |
tree | 8f9d0aaa8ac4ab09a3fa7b8891bede586aa953db /python/sandcrawler/html_ingest.py | |
parent | e61d6e8cc3b6824816a83dff56ffbdbbb6329e57 (diff) | |
download | sandcrawler-cefbc6fa46e6586d8735f40b3b5432a759edd5f1.tar.gz sandcrawler-cefbc6fa46e6586d8735f40b3b5432a759edd5f1.zip |
html: syntax fixes; resolve relative URLs; extract more XML fulltext URLs
Diffstat (limited to 'python/sandcrawler/html_ingest.py')
-rw-r--r-- | python/sandcrawler/html_ingest.py | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/python/sandcrawler/html_ingest.py b/python/sandcrawler/html_ingest.py index acd336e..284461e 100644 --- a/python/sandcrawler/html_ingest.py +++ b/python/sandcrawler/html_ingest.py @@ -6,7 +6,7 @@ import json import datetime import argparse import xml.etree.ElementTree as ET -from typing import List, Optional, Any +from typing import List, Optional, Any, Tuple import trafilatura import pydantic @@ -75,7 +75,7 @@ class IngestWebResult(pydantic.BaseModel): } -def fix_transfer_encoding(file_meta: dict, resource: ResourceResult) -> (dict, ResourceResult): +def fix_transfer_encoding(file_meta: dict, resource: ResourceResult) -> Tuple[dict, ResourceResult]: if file_meta['mimetype'] == 'application/gzip' and resource.cdx and resource.cdx.mimetype != 'application/gzip': print("transfer encoding not stripped: {}".format(resource.cdx.mimetype), file=sys.stderr) inner_body = gzip.decompress(resource.body) @@ -233,7 +233,7 @@ def run_single(url: str, timestamp: Optional[str] = None, quick_mode: bool = Fal ) html_doc = HTMLParser(html_resource.body) - html_biblio = html_extract_biblio(html_doc) + html_biblio = html_extract_biblio(url, html_doc) html_fulltext = html_extract_fulltext_teixml(html_resource.body) html_scope = html_guess_scope(url, html_doc, html_biblio, html_fulltext.get('tei_xml')) if html_scope not in ('article-fulltext', 'unknown'): |