mirror of
https://github.com/bellingcat/auto-archiver.git
synced 2026-06-10 12:18:30 +03:00
Compare commits
13 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
8624e9f177 | ||
|
|
381940f5a8 | ||
|
|
1382f8b795 | ||
|
|
fac8364762 | ||
|
|
0feeb0bd24 | ||
|
|
ddb9dc87d7 | ||
|
|
e8935b9a80 | ||
|
|
b157f9a6b1 | ||
|
|
ea38a604bb | ||
|
|
53494c961e | ||
|
|
f7839a99cc | ||
|
|
7a2119e6e9 | ||
|
|
3ae25e51e7 |
@@ -28,4 +28,4 @@ COPY ./src/ .
|
||||
ENTRYPOINT ["pipenv", "run", "python3", "-m", "auto_archiver"]
|
||||
|
||||
# should be executed with 2 volumes (3 if local_storage is used)
|
||||
# docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive aa pipenv run python3 -m auto_archiver --config secrets/orchestration.yaml
|
||||
# docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive aa pipenv run python3 -m auto_archiver --config secrets/orchestration.yaml
|
||||
|
||||
1528
Pipfile.lock
generated
1528
Pipfile.lock
generated
File diff suppressed because it is too large
Load Diff
@@ -8,8 +8,8 @@ TAG=$(python -c 'from src.auto_archiver.version import __version__; print("v" +
|
||||
read -p "Creating new release for $TAG. Do you want to continue? [Y/n] " prompt
|
||||
|
||||
if [[ $prompt == "y" || $prompt == "Y" || $prompt == "yes" || $prompt == "Yes" ]]; then
|
||||
git add -A
|
||||
git commit -m "Bump version to $TAG for release" || true && git push
|
||||
# git add -A
|
||||
# git commit -m "Bump version to $TAG for release" || true && git push
|
||||
echo "Creating new git tag $TAG"
|
||||
git tag "$TAG" -m "$TAG"
|
||||
git push --tags
|
||||
|
||||
@@ -15,8 +15,8 @@ class TwitterArchiver(Archiver):
|
||||
"""
|
||||
|
||||
name = "twitter_archiver"
|
||||
link_pattern = re.compile(r"twitter.com\/(?:\#!\/)?(\w+)\/status(?:es)?\/(\d+)")
|
||||
link_clean_pattern = re.compile(r"(.+twitter\.com\/.+\/\d+)(\?)*.*")
|
||||
link_pattern = re.compile(r"(?:twitter|x).com\/(?:\#!\/)?(\w+)\/status(?:es)?\/(\d+)")
|
||||
link_clean_pattern = re.compile(r"(.+(?:twitter|x)\.com\/.+\/\d+)(\?)*.*")
|
||||
|
||||
def __init__(self, config: dict) -> None:
|
||||
super().__init__(config)
|
||||
|
||||
@@ -27,7 +27,7 @@ class WaczArchiverEnricher(Enricher, Archiver):
|
||||
def configs() -> dict:
|
||||
return {
|
||||
"profile": {"default": None, "help": "browsertrix-profile (for profile generation see https://github.com/webrecorder/browsertrix-crawler#creating-and-using-browser-profiles)."},
|
||||
"browsertrix_home": {"default": None, "help": "path to use when calling docker run with a volume, by default it will be the tmp folder generated during execution, but setting this option is needed when running the auto-archiver in a docker container that calls another container via DooD."},
|
||||
"docker_commands": {"default": None, "help":"if a custom docker invocation is needed"},
|
||||
"timeout": {"default": 120, "help": "timeout for WACZ generation in seconds"},
|
||||
"extract_media": {"default": True, "help": "If enabled all the images/videos/audio present in the WACZ archive will be extracted into separate Media. The .wacz file will be kept untouched."}
|
||||
}
|
||||
@@ -47,51 +47,45 @@ class WaczArchiverEnricher(Enricher, Archiver):
|
||||
url = to_enrich.get_url()
|
||||
|
||||
collection = str(uuid.uuid4())[0:8]
|
||||
browsertrix_home = self.browsertrix_home or os.path.abspath(ArchivingContext.get_tmp_dir())
|
||||
browsertrix_home_host = os.environ.get('BROWSERTRIX_HOME_HOST') or os.path.abspath(ArchivingContext.get_tmp_dir())
|
||||
browsertrix_home_container = os.environ.get('BROWSERTRIX_HOME_CONTAINER') or browsertrix_home_host
|
||||
|
||||
if os.getenv('RUNNING_IN_DOCKER'):
|
||||
cmd = [
|
||||
"crawl",
|
||||
"--url", url,
|
||||
"--scopeType", "page",
|
||||
"--generateWACZ",
|
||||
"--text",
|
||||
"--screenshot", "fullPage",
|
||||
"--collection", collection,
|
||||
"--id", collection,
|
||||
"--saveState", "never",
|
||||
"--behaviors", "autoscroll,autoplay,autofetch,siteSpecific",
|
||||
"--behaviorTimeout", str(self.timeout),
|
||||
"--timeout", str(self.timeout)]
|
||||
|
||||
# call docker if explicitly enabled or we are running on the host (not in docker)
|
||||
use_docker = os.environ.get('WACZ_ENABLE_DOCKER') or not os.environ.get('RUNNING_IN_DOCKER')
|
||||
|
||||
if use_docker:
|
||||
logger.debug(f"generating WACZ in Docker for {url=}")
|
||||
logger.debug(f"{browsertrix_home_host=} {browsertrix_home_container=}")
|
||||
if self.docker_commands:
|
||||
cmd = self.docker_commands + cmd
|
||||
else:
|
||||
cmd = ["docker", "run", "--rm", "-v", f"{browsertrix_home_host}:/crawls/", "webrecorder/browsertrix-crawler"] + cmd
|
||||
|
||||
if self.profile:
|
||||
profile_fn = os.path.join(browsertrix_home_container, "profile.tar.gz")
|
||||
logger.debug(f"copying {self.profile} to {profile_fn}")
|
||||
shutil.copyfile(self.profile, profile_fn)
|
||||
cmd.extend(["--profile", os.path.join("/crawls", "profile.tar.gz")])
|
||||
|
||||
else:
|
||||
logger.debug(f"generating WACZ without Docker for {url=}")
|
||||
|
||||
cmd = [
|
||||
"crawl",
|
||||
"--url", url,
|
||||
"--scopeType", "page",
|
||||
"--generateWACZ",
|
||||
"--text",
|
||||
"--screenshot", "fullPage",
|
||||
"--collection", collection,
|
||||
"--id", collection,
|
||||
"--saveState", "never",
|
||||
"--behaviors", "autoscroll,autoplay,autofetch,siteSpecific",
|
||||
"--behaviorTimeout", str(self.timeout),
|
||||
"--timeout", str(self.timeout)]
|
||||
|
||||
if self.profile:
|
||||
cmd.extend(["--profile", os.path.join("/app", str(self.profile))])
|
||||
else:
|
||||
logger.debug(f"generating WACZ in Docker for {url=}")
|
||||
|
||||
cmd = [
|
||||
"docker", "run",
|
||||
"--rm", # delete container once it has completed running
|
||||
"-v", f"{browsertrix_home}:/crawls/",
|
||||
# "-it", # this leads to "the input device is not a TTY"
|
||||
"webrecorder/browsertrix-crawler", "crawl",
|
||||
"--url", url,
|
||||
"--scopeType", "page",
|
||||
"--generateWACZ",
|
||||
"--text",
|
||||
"--screenshot", "fullPage",
|
||||
"--collection", collection,
|
||||
"--behaviors", "autoscroll,autoplay,autofetch,siteSpecific",
|
||||
"--behaviorTimeout", str(self.timeout),
|
||||
"--timeout", str(self.timeout)
|
||||
]
|
||||
|
||||
if self.profile:
|
||||
profile_fn = os.path.join(browsertrix_home, "profile.tar.gz")
|
||||
shutil.copyfile(self.profile, profile_fn)
|
||||
cmd.extend(["--profile", os.path.join("/crawls", "profile.tar.gz")])
|
||||
|
||||
try:
|
||||
logger.info(f"Running browsertrix-crawler: {' '.join(cmd)}")
|
||||
@@ -100,18 +94,18 @@ class WaczArchiverEnricher(Enricher, Archiver):
|
||||
logger.error(f"WACZ generation failed: {e}")
|
||||
return False
|
||||
|
||||
if os.getenv('RUNNING_IN_DOCKER'):
|
||||
filename = os.path.join("collections", collection, f"{collection}.wacz")
|
||||
if use_docker:
|
||||
wacz_fn = os.path.join(browsertrix_home_container, "collections", collection, f"{collection}.wacz")
|
||||
else:
|
||||
filename = os.path.join(browsertrix_home, "collections", collection, f"{collection}.wacz")
|
||||
wacz_fn = os.path.join("collections", collection, f"{collection}.wacz")
|
||||
|
||||
if not os.path.exists(filename):
|
||||
logger.warning(f"Unable to locate and upload WACZ {filename=}")
|
||||
if not os.path.exists(wacz_fn):
|
||||
logger.warning(f"Unable to locate and upload WACZ {wacz_fn=}")
|
||||
return False
|
||||
|
||||
to_enrich.add_media(Media(filename), "browsertrix")
|
||||
to_enrich.add_media(Media(wacz_fn), "browsertrix")
|
||||
if self.extract_media:
|
||||
self.extract_media_from_wacz(to_enrich, filename)
|
||||
self.extract_media_from_wacz(to_enrich, wacz_fn)
|
||||
return True
|
||||
|
||||
def extract_media_from_wacz(self, to_enrich: Metadata, wacz_filename: str) -> None:
|
||||
|
||||
@@ -119,7 +119,7 @@ class GDriveStorage(Storage):
|
||||
'parents': [upload_to]
|
||||
}
|
||||
media = MediaFileUpload(media.filename, resumable=True)
|
||||
gd_file = self.service.files().create(body=file_metadata, media_body=media, fields='id').execute()
|
||||
gd_file = self.service.files().create(supportsAllDrives=True, body=file_metadata, media_body=media, fields='id').execute()
|
||||
logger.debug(f'uploadf: uploaded file {gd_file["id"]} successfully in folder={upload_to}')
|
||||
|
||||
# must be implemented even if unused
|
||||
@@ -150,6 +150,9 @@ class GDriveStorage(Storage):
|
||||
|
||||
for attempt in range(retries):
|
||||
results = self.service.files().list(
|
||||
# both below for Google Shared Drives
|
||||
supportsAllDrives=True,
|
||||
includeItemsFromAllDrives=True,
|
||||
q=query_string,
|
||||
spaces='drive', # ie not appDataFolder or photos
|
||||
fields='files(id, name)'
|
||||
@@ -182,7 +185,7 @@ class GDriveStorage(Storage):
|
||||
'mimeType': 'application/vnd.google-apps.folder',
|
||||
'parents': [parent_id]
|
||||
}
|
||||
gd_folder = self.service.files().create(body=file_metadata, fields='id').execute()
|
||||
gd_folder = self.service.files().create(supportsAllDrives=True, body=file_metadata, fields='id').execute()
|
||||
return gd_folder.get('id')
|
||||
|
||||
# def exists(self, key):
|
||||
|
||||
@@ -65,6 +65,9 @@ class UrlUtil:
|
||||
if "vk.com/images/" in url: return False
|
||||
if "vk.com/images/reaction/" in url: return False
|
||||
|
||||
# wikipedia
|
||||
if "wikipedia.org/static" in url: return False
|
||||
|
||||
return True
|
||||
|
||||
@staticmethod
|
||||
|
||||
@@ -15,7 +15,7 @@ class Webdriver:
|
||||
|
||||
def __enter__(self) -> webdriver:
|
||||
options = webdriver.FirefoxOptions()
|
||||
options.headless = True
|
||||
options.add_argument("--headless")
|
||||
options.set_preference('network.protocol-handler.external.tg', False)
|
||||
try:
|
||||
self.driver = webdriver.Firefox(options=options)
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
|
||||
_MAJOR = "0"
|
||||
_MINOR = "6"
|
||||
_MINOR = "7"
|
||||
# On main and in a nightly release the patch should be one ahead of the last
|
||||
# released build.
|
||||
_PATCH = "8"
|
||||
_PATCH = "1"
|
||||
# This is mainly for nightly builds which have the suffix ".dev$DATE". See
|
||||
# https://semver.org/#is-v123-a-semantic-version for the semantics.
|
||||
_SUFFIX = ""
|
||||
|
||||
Reference in New Issue
Block a user