def second_level_topics():
second_level_topics = []
for topic in top_level_topics:
second_level_topic_data = parser.parse_url(topic["api_url"])
for second_level_topic in second_level_topic_data["links"]["children"]:
second_level_topics.append(second_level_topic)
return second_level_topics
"specialist_sectors": ["array of items"],
"title": "the titles",
"document_type": "document type"
}
Then go through all the links with https://www.gov.uk/api/content/#{link}
and collect content ids
'''
from api_paginator import ApiPaginator
import page_parser as parser
ROOT_URL_OF_ITEMS_WITHOUT_TAG = "https://www.gov.uk/api/search.json?filter_specialist_sectors=_MISSING"
ROOT_URL_OF_ITEMS_WITH_TAG = "https://www.gov.uk/api/search.json?reject_specialist_sectors=_MISSING"
parsed_root = parser.parse_url(ROOT_URL_OF_ITEMS_WITH_TAG)
paginator = ApiPaginator(ROOT_URL_OF_ITEMS_WITH_TAG)
# count items, I don't wanna store this variable here,
# so this method should set an internal variable rather than returning a value
item_count = paginator.items_total(parsed_root)
# tell paginator to count items, this should be done by the pagintaor itself
# move this within another method in the paginator
paginator.calculate_pages(item_count)
page_urls = paginator.page_urls()
import json
fo = open('data/items_with_tag.jsonl', "w+")
for page_url in page_urls:
'''
This script parses first and second level topic's data from GOV.UK's API.
Current output:
some logging and the total number of first and second level topics.
'''
import page_parser as parser
ROOT_URL = "https://www.gov.uk/api/content/topic"
def second_level_topics():
second_level_topics = []
for topic in top_level_topics:
second_level_topic_data = parser.parse_url(topic["api_url"])
for second_level_topic in second_level_topic_data["links"]["children"]:
second_level_topics.append(second_level_topic)
return second_level_topics
top_level_topics = parser.parse_url(ROOT_URL)["links"]["children"]
second_level_topics = second_level_topics()
print("\nTotal number of first level topics: %d" % len(top_level_topics))
print("\nTotal number of second level topics: %d" % len(second_level_topics))
redirects and the content is available on the regular site
'''
import page_parser as parser
import json
import time
ROOT_URL = "https://www.gov.uk/api/content"
# this is bad because it stores the whole file in a variable
lines = [line.rstrip('\n') for line in open('items_with_tag.jsonl')]
fo = open('items_with_tag_and_content_id.jsonl', "w+")
for line in lines:
try:
json_line = json.loads(line)
if 'content_id' not in json_line:
link = json_line['link']
time.sleep(1)
parsed_item = parser.parse_url(ROOT_URL + link)
item_content_id = parsed_item['content_id']
json_line['content_id'] = item_content_id
fo.write( json.dumps(json_line) + "\n" )
print("processed: " + item_content_id)
else:
print("key present in:" + line[:50])
except:
fo.write( item_content_id + "\n" )
print("failed: " + item_content_id)
fo.close()