Skip to content

Added WAYBACK_MACHINE_FIELDS setting #12

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
shanept wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Added WAYBACK_MACHINE_FIELDS setting #12

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ad526ef
Added WAYBACK_MACHINE_FIELDS setting
shanept Feb 18, 2024
bcc0af2
Fixed scrapy.engine.schedule deprecation
shanept Jan 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 28 additions & 4 deletions scrapy_wayback_machine/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,8 @@ class UnhandledIgnoreRequest(IgnoreRequest):

class WaybackMachineMiddleware:
cdx_url_template = ('https://web.archive.org/cdx/search/cdx?url={url}'
'&output=json&fl=timestamp,original,statuscode,digest')
'&output=json&fl={fields}')
cdx_fields = ['timestamp','original','statuscode','digest']
snapshot_url_template = 'https://web.archive.org/web/{timestamp}id_/{original}'
robots_txt = 'https://web.archive.org/robots.txt'
timestamp_format = '%Y%m%d%H%M%S'
Expand All @@ -29,6 +30,13 @@ def __init__(self, crawler):
raise NotConfigured
self.set_time_range(time_range)

# If the WAYBACK_MACHINE_FIELDS settings has not been defined,
# we default to the existing value
extra_fields = crawler.settings.get('WAYBACK_MACHINE_FIELDS', self.cdx_fields)

# Merge the new values in if they are unique
self.cdx_fields.extend(f for f in extra_fields if f not in self.cdx_fields)

def set_time_range(self, time_range):
# allow a single time to be passed in place of a range
if type(time_range) not in [tuple, list]:
Expand Down Expand Up @@ -80,7 +88,7 @@ def process_response(self, request, response, spider):

# schedule all of the snapshots
for snapshot_request in snapshot_requests:
self.crawler.engine.schedule(snapshot_request, spider)
self.crawler.engine.crawl(snapshot_request)

# abort this request
raise UnhandledIgnoreRequest
Expand All @@ -93,9 +101,16 @@ def process_response(self, request, response, spider):

def build_cdx_request(self, request):
if os.name == 'nt':
cdx_url = self.cdx_url_template.format(url=pathname2url(request.url.split('://')[1]))
cdx_url = pathname2url(request.url.split('://')[1])
else:
cdx_url = self.cdx_url_template.format(url=pathname2url(request.url))
cdx_url = pathname2url(request.url)


cdx_url = self.cdx_url_template.format(
url = cdx_url,
fields = ','.join(self.cdx_fields)
)

cdx_request = Request(cdx_url)
cdx_request.meta['wayback_machine_original_request'] = request
cdx_request.meta['wayback_machine_cdx_request'] = True
Expand Down Expand Up @@ -142,6 +157,15 @@ def build_dict(row):
'wayback_machine_time': snapshot['datetime'],
})

# Add snapshot metadata into the request object
for k,v in snapshot.items():
if k in ['datetime', 'timestamp', 'statuscode']:
continue

snapshot_request.meta.update({
'wayback_machine_' + k: v
})

snapshot_requests.append(snapshot_request)

return snapshot_requests
Expand Down