From ab4e1355bf93e3755985f1b5cd2589a78601d253 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 10 Nov 2021 13:08:23 -0800 Subject: remove cdl_dash_dat and wayback_static importers Cleaning out dead code. These importers were used to create demonstration fileset and webcapture entities early in development. They have been replaced by the fileset and webcapture ingest importers. --- python/fatcat_tools/importers/wayback_static.py | 287 ------------------------ 1 file changed, 287 deletions(-) delete mode 100755 python/fatcat_tools/importers/wayback_static.py (limited to 'python/fatcat_tools/importers/wayback_static.py') diff --git a/python/fatcat_tools/importers/wayback_static.py b/python/fatcat_tools/importers/wayback_static.py deleted file mode 100755 index 5caed2c7..00000000 --- a/python/fatcat_tools/importers/wayback_static.py +++ /dev/null @@ -1,287 +0,0 @@ -#!/usr/bin/env python3 - -""" -Helpers to create Web Capture entities from extracted wayback content. - -Works as a stand-alone script (for debugging) or as library routines. -""" - -import argparse -import datetime -import hashlib -import json -import subprocess -import sys -from typing import Any, Dict, List, Optional, Tuple - -import requests -from bs4 import BeautifulSoup -from fatcat_openapi_client import ( - ApiClient, - Editgroup, - EntityEdit, - WebcaptureCdxLine, - WebcaptureEntity, - WebcaptureUrl, -) - -from .common import b32_hex - -CDX_API_BASE = "https://web.archive.org/cdx/search/cdx" -GWB_URL_BASE = "https://web.archive.org/web" -REQ_SESSION = requests.Session() - - -def parse_wbm_url(url: str) -> Tuple[str, datetime.datetime, str]: - """Takes a wayback machine URL, and returns a tuple: - - (timestamp, datetime, original_url) - """ - chunks = url.split("/") - assert len(chunks) >= 6 - assert chunks[2] == "web.archive.org" - assert chunks[3] == "web" - return (chunks[4], parse_wbm_timestamp(chunks[4]), "/".join(chunks[5:])) - - -def test_parse_wbm_url() -> None: - u = "http://web.archive.org/web/20010712114837/http://www.dlib.org/dlib/june01/reich/06reich.html" - assert parse_wbm_url(u) == ( - "20010712114837", - datetime.datetime(2001, 7, 12, 11, 48, 37), - "http://www.dlib.org/dlib/june01/reich/06reich.html", - ) - - -def parse_wbm_timestamp(timestamp: str) -> datetime.datetime: - """ - Takes a complete WBM timestamp string (like "20020327115625") and returns a - python datetime object (UTC) - """ - # strip any "im_" or "id_" suffix - if timestamp.endswith("_"): - timestamp = timestamp[:-3] - # inflexible; require the full second-precision timestamp - assert len(timestamp) == 14 - return datetime.datetime( - year=int(timestamp[0:4]), - month=int(timestamp[4:6]), - day=int(timestamp[6:8]), - hour=int(timestamp[8:10]), - minute=int(timestamp[10:12]), - second=int(timestamp[12:14]), - ) - - -def test_parse_wbm_timestamp() -> None: - assert parse_wbm_timestamp("20010712114837") == datetime.datetime(2001, 7, 12, 11, 48, 37) - - -def fetch_wbm(url: str) -> bytes: - resp = REQ_SESSION.get(url) - resp.raise_for_status() - assert resp.content - return resp.content - - -def lookup_cdx( - embed_url: str, verify_hashes: bool = True, cdx_output: Any = None -) -> Optional[WebcaptureCdxLine]: - sys.stderr.write(embed_url + "\n") - assert embed_url.startswith("/web/") - embed_url_segments = embed_url.split("/") - timestamp = embed_url_segments[2] - if timestamp.endswith("_"): - timestamp = timestamp[:-3] - url = "/".join(embed_url_segments[3:]) - # print((timestamp, url)) - params: Dict = dict( - url=url, - closest=timestamp, - sort="closest", - resolveRevisits="true", - matchType="exact", - limit=1, - ) - resp = REQ_SESSION.get( - CDX_API_BASE, - params=params, - ) - resp.raise_for_status() - # print(resp.url) - if resp.content: - hit = resp.content.decode("utf-8").split("\n")[0] - if cdx_output: - cdx_output.write(hit + "\n") - cdx_chunks = hit.split(" ") - cdx = [x if (x and x != "-") else None for x in cdx_chunks] - webcapture_cdx = WebcaptureCdxLine( - surt=cdx[0], - timestamp=parse_wbm_timestamp(cdx[1] or "").isoformat() + "Z", - url=cdx[2], - mimetype=cdx[3], - status_code=int(cdx[4] or ""), - sha1=b32_hex(cdx[5] or ""), - sha256=None, - ) - if verify_hashes: - resp = REQ_SESSION.get( - GWB_URL_BASE + "/{}id_/{}".format(cdx[1], webcapture_cdx.url) # raw timestamp - ) - resp.raise_for_status() - assert webcapture_cdx.sha1 == hashlib.sha1(resp.content).digest().hex() - webcapture_cdx.sha256 = hashlib.sha256(resp.content).digest().hex() - webcapture_cdx.size = len(resp.content) - return webcapture_cdx - else: - return None - - -def wayback_url_to_relative(url: str) -> Optional[str]: - """ - Wayback URLs can be relative or absolute in rewritten documents. This - function converts any form of rewritten URL to a relative (to - web.archive.org) one, or returns None if it isn't a rewritten URL at all. - """ - if url.startswith("https://web.archive.org/"): - url = url[23:] - elif url.startswith("http://web.archive.org/"): - url = url[22:] - - if url.startswith("/web/"): - return url - else: - return None - - -def extract_embeds(soup: BeautifulSoup) -> List[str]: - - embeds = set() - - # - for tag in soup.find_all("link", href=True): - if tag["rel"] not in ("stylesheet",): - continue - url = wayback_url_to_relative(tag["href"]) - if url: - embeds.add(url) - # - for tag in soup.find_all("img", src=True): - url = wayback_url_to_relative(tag["src"]) - if url: - embeds.add(url) - - #