def render():
req_url = request.args.get('url')
if not req_url:
return build_error_response(message="Error! No page specified!")
req_url = request.args.get('url')
version = request.args.get('version')
ignore_cache = request.args.get("nocache")
filterstate = get_filter_state_for_url(req_url)
try:
if version == "None":
version = None
else:
version = ast.literal_eval(version)
except ValueError:
return build_error_response(
message="Error! Historical version number must be an integer!")
if version and ignore_cache:
return build_error_response(
message="Error! Cannot render a historical version with nocache!")
if version:
rid, tid = version
print("Historical row id: ", rid, tid)
ctbl = version_table(db.WebPages)
rows = g.session.query(ctbl.c.title, ctbl.c.content) \
.filter(ctbl.c.id == rid) \
.filter(ctbl.c.transaction_id == tid) \
.all()
if rows:
row = rows.pop()
title, content = row
content = utilities.replace_links(content)
cachestate = "Historical version: %s" % (version, )
else:
title, content, cachestate = WebMirror.API.getPage(
req_url, ignore_cache=ignore_cache, version=version)
# print("Render-Version: ", version, type(version))
# print("Rendering with nocache=", ignore_cache)
# print("Return:", cachestate)
response = jsonify(
title=title,
contents=content,
cachestate=cachestate,
filterstate=filterstate,
req_url=req_url,
)
return set_cache_control_headers(response)
def getContent(self, relink_replace):
"""
At this point, we have the page content, but we need to
replace the url/resource keys with the proper paths
so that the page will render properly
"""
assert self.fetched
content = self.job.content
if content and relink_replace:
content = utilities.replace_links(content)
return content
def processRaw(self,
content,
mimetype='text/html',
starturl='http://www.example.org'):
# Abuse the fact that functions (including lambda) are fully formed objects
job = lambda: None
job.url = self.url
job.starturl = "http://www.example.org"
job.distance = common.database.MAX_DISTANCE - 2
fetcher = self.archiver.fetcher(self.archiver.ruleset,
target_url=job.url,
start_url=job.starturl,
db_sess=self.archiver.db_sess,
job=job,
cookie_lock=False)
print(fetcher)
ret = fetcher.dispatchContent(content, "None", "text/html")
content = ret['contents']
content = utilities.replace_links(content)
return content
def view_rendered():
req_url = request.args.get('url')
if not req_url:
return render_template('error.html',
title='Error',
message="Error! No page specified!")
req_url = request.args.get('url')
version = request.args.get('version')
ignore_cache = request.args.get("nocache")
filterstate = get_filter_state_for_url(req_url)
try:
if version == "None" or version is None:
version = None
else:
version = ast.literal_eval(version)
except ValueError:
traceback.print_exc()
return render_template(
'error.html',
title='Error',
message="Error! Historical version number must be an integer!")
if version and ignore_cache:
return render_template(
'error.html',
title='Error',
message="Error! Cannot render a historical version with nocache!")
if version:
rid, tid = version
print("Historical row id: ", rid, tid)
ctbl = version_table(db.WebPages.__table__)
rows = g.session.query(ctbl.c.title, ctbl.c.content) \
.filter(ctbl.c.id == rid) \
.filter(ctbl.c.transaction_id == tid) \
.all()
if rows:
row = rows.pop()
title, content = row
content = utilities.replace_links(content)
cachestate = "Historical version: %s" % (version, )
else:
title, content, cachestate = WebMirror.API.getPage(
req_url, ignore_cache=ignore_cache, version=version)
response = make_response(
render_template(
'view-rendered.html',
req_url=req_url,
version=version,
title=title,
contents=content,
cachestate=cachestate,
filterstate=filterstate,
))
return set_cache_control_headers(response, allow_inline=True)