def load_archive_info_xml(self, url):
self.archive_infos = {}
logging.debug('Loading XML from {0}'.format(url))
if not url:
return
try:
stream = BlockLoader().load(url)
except Exception as e:
logging.debug(e)
logging.debug('Proceeding without xml archive info')
return
root = ElementTree.fromstring(stream.read())
for link in root.findall('link'):
name = link.get('id')
archive = link.find('archive')
timegate = link.find('timegate')
if timegate is None or archive is None:
continue
rewritten = (archive.get('rewritten-urls') == 'yes')
unrewritten_url = archive.get('un-rewritten-api-url', '')
uri = timegate.get('uri')
self.archive_infos[name] = {'uri': uri,
'rewritten': rewritten,
'unrewritten_url': unrewritten_url
}
def load_archive_info_json(self, url):
self.archive_infos = {}
url = os.path.expandvars(url)
logging.debug('Loading XML from {0}'.format(url))
if not url:
return
try:
stream = BlockLoader().load(url)
except Exception as e:
logging.debug(e)
logging.debug('Proceeding without json archive info')
return
archives = json.loads(stream.read())
for arc in archives:
id_ = arc['id']
name = arc['name']
uri = arc['timegate']
base_url = arc.get('base_url', uri)
unrewritten_url = arc.get('unrewritten_url')
if not unrewritten_url:
unrewritten_url = base_url + '{timestamp}id_/{url}'
self.archive_infos[id_] = {
'id': id_,
'uri': uri,
'name': name,
'base_url': base_url,
'unrewritten_url': unrewritten_url
}
def load_archive_info_xml(self, url):
self.archive_infos = {}
url = os.path.expandvars(url)
logging.debug('Loading XML from {0}'.format(url))
if not url:
return
try:
stream = BlockLoader().load(url)
except Exception as e:
logging.debug(e)
logging.debug('Proceeding without xml archive info')
return
root = ElementTree.fromstring(stream.read())
for link in root.findall('link'):
name = link.get('id')
longname = link.get('longname')
archive = link.find('archive')
timegate = link.find('timegate')
if timegate is None or archive is None:
continue
rewritten = (archive.get('rewritten-urls') == 'yes')
unrewritten_url = archive.get('un-rewritten-api-url', '')
uri = timegate.get('uri')
self.archive_infos[name] = {
'uri': uri,
'rewritten': rewritten,
'unrewritten_url': unrewritten_url,
'name': longname
}
def load_archive_info_json(self, url):
self.archive_infos = {}
url = os.path.expandvars(url)
logging.debug('Loading XML from {0}'.format(url))
if not url:
return
try:
stream = BlockLoader().load(url)
except Exception as e:
logging.debug(e)
logging.debug('Proceeding without json archive info')
return
archives = json.loads(stream.read())
for arc in archives:
id_ = arc['id']
name = arc['name']
uri = arc['timegate']
unrewritten_url = arc.get('unrewritten_url')
if not unrewritten_url:
unrewritten_url = uri + '{timestamp}id_/{url}'
self.archive_infos[id_] = {'id': id_,
'uri': uri,
'name': name,
'rewritten': True,
'unrewritten_url': unrewritten_url}
def test_s3_read_2():
pytest.importorskip('boto3')
res = BlockLoader().load('s3://commoncrawl/crawl-data/CC-MAIN-2015-11/index.html')
buff = res.read()
assert len(buff) == 2082
reader = DecompressingBufferedReader(BytesIO(buff))
assert reader.readline() == b'<!DOCTYPE html>\n'
def test_s3_read_2():
pytest.importorskip('boto3')
res = BlockLoader().load('s3://commoncrawl/crawl-data/CC-MAIN-2015-11/index.html')
buff = res.read()
assert len(buff) == 2082
reader = DecompressingBufferedReader(BytesIO(buff))
assert reader.readline() == b'<!DOCTYPE html>\n'
def test_s3_read_1():
pytest.importorskip('boto')
res = BlockLoader().load('s3://commoncrawl/crawl-data/CC-MAIN-2015-11/segments/1424936462700.28/warc/CC-MAIN-20150226074102-00159-ip-10-28-5-156.ec2.internal.warc.gz',
offset=53235662,
length=2526)
buff = res.read()
assert len(buff) == 2526
reader = DecompressingBufferedReader(BytesIO(buff))
assert reader.readline() == b'WARC/1.0\r\n'
assert reader.readline() == b'WARC-Type: response\r\n'
def test_s3_read_1():
pytest.importorskip('boto')
res = BlockLoader().load('s3://aws-publicdatasets/common-crawl/crawl-data/CC-MAIN-2015-11/segments/1424936462700.28/warc/CC-MAIN-20150226074102-00159-ip-10-28-5-156.ec2.internal.warc.gz',
offset=53235662,
length=2526)
buff = res.read()
assert len(buff) == 2526
reader = DecompressingBufferedReader(BytesIO(buff))
assert reader.readline() == b'WARC/1.0\r\n'
assert reader.readline() == b'WARC-Type: response\r\n'
