I'm trying to extract a specific string value from a text file (file1.txt) and then to create HTTP GET request with the extracted string (url address), the HTTP response should be saved as a new HTML file in the directory. The string I'm trying to extract is a value of a specific key.
For example: "display_url":"test.com" (extract "test.com" and then to create http request)
My txt file content:
{"created_at":"Thu Nov 15 11:35:00 +0000 2018","id":15292802,"id_str":325802","text":"test8 https://t.co/ZtCsuk7Ek2 #osining","source":"\u003ca href=\"http://twitter.com\" rel=\"nofollow\"\u003eTwitter Web Client\u003c/a\u003e","truncated":false,"in_reply_to_status_id":null,"in_reply_to_status_id_str":null,"in_reply_to_user_id":null,"in_reply_to_user_id_str":null,"in_reply_to_screen_name":null,"user":{"id":961508561217052675,"id_str":"961508561217052675","name":"Online S","screen_name":"osectraining","location":"Israel","url":"https://www.test.co.il","description":"test","translator_type":"none","protected":false,"verified":false,"followers_count":2,"friends_count":51,"listed_count":0,"favourites_count":0,"statuses_count":7,"created_at":"Thu Feb 08 07:54:39 +0000 2018","utc_offset":null,"time_zone":null,"geo_enabled":false,"lang":"en","contributors_enabled":false,"is_translator":false,"profile_background_color":"000000","profile_background_image_url":"http://abs.twimg.com/images/themes/theme1/bg.png","profile_background_image_url_https":"https://abs.twimg.com/images/themes/theme1/bg.png","profile_background_tile":false,"profile_link_color":"1B95E0","profile_sidebar_border_color":"000000","profile_sidebar_fill_color":"000000","profile_text_color":"000000","profile_use_background_image":false,"profile_image_url":"http://pbs.twimg.com/profile_images/961510231346958336/d_KhBeTD_normal.jpg","profile_image_url_https":"https://pbs.twimg.com/profile_images/961510231346958336/d_KhBeTD_normal.jpg","profile_banner_url":"https://pbs.twimg.com/profile_banners/961508561217052675/1518076913","default_profile":false,"default_profile_image":false,"following":null,"follow_request_sent":null,"notifications":null},"geo":null,"coordinates":null,"place":null,"contributors":null,"is_quote_status":false,"quote_count":0,"reply_count":0,"retweet_count":0,"favorite_count":0,"entities":{"hashtags":[{"text":"osectraining","indices":[33,46]}],"urls":[{"url":"https://t.co/ZtCsuk7Ek2","expanded_url":"http://test.com","display_url":"test.com","indices":[7,30]}],"user_mentions":[],"symbols":[]},"favorited":false,"retweeted":false,"possibly_sensitive":false,"filter_level":"low","lang":"en","timestamp_ms":"1542281700508"}
My code:
import re
with open('file1') as f:
found = []
for line in f.readlines():
found += re.findall(r'"display_url":\s(\w+)\s', line)
print(found)