def augment_trip_plan(raw_trip_plan):
location_latlng = raw_trip_plan.location_latlng.to_json_obj() if raw_trip_plan.location_latlng else None
entities = utils.parallelize(
utils.retryable(augment_entity, retries=3),
[(e, location_latlng) for e in raw_trip_plan.entities])
trip_plan = raw_trip_plan.copy()
for i, entity in enumerate(entities):
# If there's an RPC error, some of these may come back as None.
# So as a fallback make sure we at least save the incoming entity.
# TODO: Return an error message here so the user can be notified
# that not all entities were saved.
if not entity:
entities[i] = raw_trip_plan.entities[i]
trip_plan.entities = entities
return trip_plan
def build_scrapers(url, client_page_source=None, force_fetch_page=False, allow_expansion=True, for_guide=False):
page_source_tree = html_parsing.parse_tree_from_string(client_page_source) if client_page_source else None
if not page_source_tree and (url_requires_server_page_source(url) or force_fetch_page):
page_source_tree = html_parsing.parse_tree(url)
scraped_pages = []
for scraper_class in ALL_SCRAPERS:
handleable_urls = scraper_class.handleable_urls(url, page_source_tree, allow_expansion)
if handleable_urls:
reqs = [html_parsing.make_request(u) for u in handleable_urls]
resps = utils.parallelize(utils.retryable(urllib2.urlopen, 3), [(req,) for req in reqs])
for url, resp in zip(handleable_urls, resps):
if not resp:
print "Failed to fetch url: %s" % url
continue
tree = etree.parse(resp, html_parsing.htmlparser())
scraper = scraper_class(url, tree, for_guide)
scraped_pages.append(scraper)
break
return scraped_pages
