add basic scraper functionality, change input_country function to ret…

…urn alpha_3 for the scraper
kronicka · Dec 29, 2018 · 0c0a816 · 0c0a816
1 parent a4b77cd
commit 0c0a816
Show file tree

Hide file tree

Showing 3 changed files with 28 additions and 8 deletions.
diff --git a/app.py b/app.py
@@ -68,8 +68,11 @@ def input_country() -> str:
         country = input('Enter your country (full name or 2-letter alias):\n')
         country_names = [country.name for country in countries]
         country_codes = [country.alpha_2 for country in countries]
-        if country.capitalize() in country_names or country.upper() in country_codes:
-            return country
+
+        if country.capitalize() in country_names:
+            return countries.get(name=country.capitalize()).alpha_3
+        elif country.upper() in country_codes:
+            return countries.get(alpha_2=country.upper()).alpha_3
         else:
             print('Please enter a valid country name.')
 
@@ -128,8 +131,11 @@ def generate_calendar(units: int, unit_type: str = None):
 
 
 if __name__ == '__main__':
-    dob = input_dob()
+    # dob = input_dob()
     # sex = input_sex()
     # weeks = calculate_weeks(sex, *dob)
-    days = calculate_days(*dob)
-    generate_calendar(days, 'days')
+    # days = calculate_days(*dob)
+    # generate_calendar(days, 'days')
+    c = input_country()
+    print(c)
+
diff --git a/requirements.txt b/requirements.txt
@@ -1,4 +1,5 @@
 bs4
 Pillow>=5.3.0
 python-dateutil
-pycountry>=18.12.8
+pycountry>=18.12.8
+requests
diff --git a/scraper.py b/scraper.py
@@ -1,7 +1,20 @@
 # Scraper of the The World Bank most recent life expectancy stats
 # for when the prediction based on the country is made
 from bs4 import BeautifulSoup
+import requests
 
-soup = BeautifulSoup('<html><body><b>Hi</b></body></html>', 'html.parser')
+country = 'RUS'
+widget_url = 'https://databank.worldbank.org/data/views/reports/reportwidget.aspx'
+report_url = f'?Report_Name=CountryProfile&Id=b450fd57&tbar=y&dd=y&inf=n&zm=n&country={country}'
+data_url = widget_url + report_url
 
-print(soup.body)
+response = requests.get(data_url)
+
+onclick_value = "loadMetaData('SP.DYN.LE00.IN','S','Series','Life expectancy at birth, total (years)','2','1801')"
+soup = BeautifulSoup(response.text, 'html.parser') \
+                    .find(attrs={'onclick': onclick_value}) \
+                    .parent \
+                    .find_all('td')[-1] \
+                    .find('div').get_text()
+
+print(soup)