browsertrix/backend/btrixcloud/zip.py
Tessa Walsh 14189b7cfb
Add crawl pages and related API endpoints (#1516)
Fixes #1502 

- Adds pages to database as they get added to Redis during crawl
- Adds migration to add pages to database for older crawls from
pages.jsonl and extraPages.jsonl files in WACZ
- Adds GET, list GET, and PATCH update endpoints for pages
- Adds POST (add), PATCH, and POST (delete) endpoints for page notes,
each with their own id, timestamp, and user info in addition to text
- Adds page_ops methods for 1. adding resources/urls to page, and 2.
adding automated heuristics and supplemental info (mime, type, etc.) to
page (for use in crawl QA job)
- Modifies `Migration` class to accept kwargs so that we can pass in ops
classes as needed for migrations
- Deletes WACZ files and pages from database for failed crawls during
crawl_finished process
- Deletes crawl pages when a crawl is deleted

Note: Requires a crawler version 1.0.0 beta3 or later, with support for
`--writePagesToRedis` to populate pages at crawl completion. Beta 4 is
configured in the test chart, which should be upgraded to stable 1.0.0
when it's released.

Connected to https://github.com/webrecorder/browsertrix-crawler/pull/464

---------

Co-authored-by: Ilya Kreymer <ikreymer@gmail.com>
2024-02-28 12:11:35 -05:00

201 lines
6.4 KiB
Python

"""
Methods for interacting with zip/WACZ files
"""
import io
import struct
import zipfile
import zlib
# ============================================================================
EOCD_RECORD_SIZE = 22
ZIP64_EOCD_RECORD_SIZE = 56
ZIP64_EOCD_LOCATOR_SIZE = 20
MAX_STANDARD_ZIP_SIZE = 4_294_967_295
CHUNK_SIZE = 1024 * 256
# ============================================================================
def sync_get_filestream(client, bucket, key, file_zipinfo, cd_start):
"""Return uncompressed byte stream of file in WACZ"""
# pylint: disable=too-many-locals
file_head = sync_fetch(
client, bucket, key, cd_start + file_zipinfo.header_offset + 26, 4
)
name_len = parse_little_endian_to_int(file_head[0:2])
extra_len = parse_little_endian_to_int(file_head[2:4])
content = sync_fetch_stream(
client,
bucket,
key,
cd_start + file_zipinfo.header_offset + 30 + name_len + extra_len,
file_zipinfo.compress_size,
)
decompress = False
if file_zipinfo.compress_type == zipfile.ZIP_DEFLATED:
decompress = True
return sync_iter_lines(content, decompress=decompress)
def sync_iter_lines(chunk_iter, decompress=False, keepends=True):
"""
Iter by lines, adapted from botocore
"""
pending = b""
for chunk in chunk_iter:
if decompress:
chunk = zlib.decompressobj(-zlib.MAX_WBITS).decompress(chunk)
lines = (pending + chunk).splitlines(True)
for line in lines[:-1]:
yield line.splitlines(keepends)[0]
pending = lines[-1]
if pending:
yield pending.splitlines(keepends)[0]
async def get_zip_file(client, bucket, key):
"""Fetch enough of the WACZ file be able to read the zip filelist"""
file_size = await get_file_size(client, bucket, key)
eocd_record = await fetch(
client, bucket, key, file_size - EOCD_RECORD_SIZE, EOCD_RECORD_SIZE
)
if file_size <= MAX_STANDARD_ZIP_SIZE:
cd_start, cd_size = get_central_directory_metadata_from_eocd(eocd_record)
central_directory = await fetch(client, bucket, key, cd_start, cd_size)
return (
cd_start,
zipfile.ZipFile(io.BytesIO(central_directory + eocd_record)),
)
zip64_eocd_record = await fetch(
client,
bucket,
key,
file_size
- (EOCD_RECORD_SIZE + ZIP64_EOCD_LOCATOR_SIZE + ZIP64_EOCD_RECORD_SIZE),
ZIP64_EOCD_RECORD_SIZE,
)
zip64_eocd_locator = await fetch(
client,
bucket,
key,
file_size - (EOCD_RECORD_SIZE + ZIP64_EOCD_LOCATOR_SIZE),
ZIP64_EOCD_LOCATOR_SIZE,
)
cd_start, cd_size = get_central_directory_metadata_from_eocd64(zip64_eocd_record)
central_directory = await fetch(client, bucket, key, cd_start, cd_size)
return (
cd_start,
zipfile.ZipFile(
io.BytesIO(
central_directory + zip64_eocd_record + zip64_eocd_locator + eocd_record
)
),
)
def sync_get_zip_file(client, bucket, key):
"""Fetch enough of the WACZ file be able to read the zip filelist"""
file_size = sync_get_file_size(client, bucket, key)
eocd_record = sync_fetch(
client, bucket, key, file_size - EOCD_RECORD_SIZE, EOCD_RECORD_SIZE
)
if file_size <= MAX_STANDARD_ZIP_SIZE:
cd_start, cd_size = get_central_directory_metadata_from_eocd(eocd_record)
central_directory = sync_fetch(client, bucket, key, cd_start, cd_size)
with zipfile.ZipFile(io.BytesIO(central_directory + eocd_record)) as zip_file:
return (cd_start, zip_file)
zip64_eocd_record = sync_fetch(
client,
bucket,
key,
file_size
- (EOCD_RECORD_SIZE + ZIP64_EOCD_LOCATOR_SIZE + ZIP64_EOCD_RECORD_SIZE),
ZIP64_EOCD_RECORD_SIZE,
)
zip64_eocd_locator = sync_fetch(
client,
bucket,
key,
file_size - (EOCD_RECORD_SIZE + ZIP64_EOCD_LOCATOR_SIZE),
ZIP64_EOCD_LOCATOR_SIZE,
)
cd_start, cd_size = get_central_directory_metadata_from_eocd64(zip64_eocd_record)
central_directory = sync_fetch(client, bucket, key, cd_start, cd_size)
with zipfile.ZipFile(
io.BytesIO(
central_directory + zip64_eocd_record + zip64_eocd_locator + eocd_record
)
) as zip_file:
return (cd_start, zip_file)
async def get_file_size(client, bucket, key):
"""Get WACZ file size from HEAD request"""
head_response = await client.head_object(Bucket=bucket, Key=key)
return head_response["ContentLength"]
def sync_get_file_size(client, bucket, key):
"""Get WACZ file size from HEAD request"""
head_response = client.head_object(Bucket=bucket, Key=key)
return head_response["ContentLength"]
async def fetch(client, bucket, key, start, length):
"""Fetch a byte range from a file in object storage"""
end = start + length - 1
response = await client.get_object(
Bucket=bucket, Key=key, Range=f"bytes={start}-{end}"
)
return await response["Body"].read()
def sync_fetch(client, bucket, key, start, length):
"""Fetch a byte range from a file in object storage"""
end = start + length - 1
response = client.get_object(Bucket=bucket, Key=key, Range=f"bytes={start}-{end}")
return response["Body"].read()
def sync_fetch_stream(client, bucket, key, start, length):
"""Fetch a byte range from a file in object storage as a stream"""
end = start + length - 1
response = client.get_object(Bucket=bucket, Key=key, Range=f"bytes={start}-{end}")
return response["Body"].iter_chunks(chunk_size=CHUNK_SIZE)
def get_central_directory_metadata_from_eocd(eocd):
"""Get central directory start and size"""
cd_size = parse_little_endian_to_int(eocd[12:16])
cd_start = parse_little_endian_to_int(eocd[16:20])
return cd_start, cd_size
def get_central_directory_metadata_from_eocd64(eocd64):
"""Get central directory start and size for zip64"""
cd_size = parse_little_endian_to_int(eocd64[40:48])
cd_start = parse_little_endian_to_int(eocd64[48:56])
return cd_start, cd_size
def parse_little_endian_to_int(little_endian_bytes):
"""Convert little endian used in zip spec to int"""
byte_length = len(little_endian_bytes)
format_character = "q"
if byte_length == 4:
format_character = "i"
elif byte_length == 2:
format_character = "h"
return struct.unpack("<" + format_character, little_endian_bytes)[0]