dtomlinson/geography-anki
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

chore: debug anthem

Browse Source
This commit is contained in:
Daniel Tomlinson
2022-06-24 00:08:38 +01:00
parent 4b36736990
commit 7e1b87ff06
3 changed files with 3609 additions and 325 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
01_scrapy/wikipedia_country_scraper/wikipedia_country_scraper/items.py
View File

@@ -12,6 +12,8 @@ class WikipediaCountryScraperItem(scrapy.Item):
country = scrapy.Field() country = scrapy.Field()
flag_description = scrapy.Field() flag_description = scrapy.Field()
anthem = scrapy.Field() anthem = scrapy.Field()
anthem_url = scrapy.Field()
anthem_file_url = scrapy.Field()
file_urls = scrapy.Field() file_urls = scrapy.Field()
files = scrapy.Field() files = scrapy.Field()

2
01_scrapy/wikipedia_country_scraper/wikipedia_country_scraper/spiders/countrydownloader.py
View File

@@ -108,6 +108,8 @@ class CountrydownloaderSpider(scrapy.Spider):
country_scrapy_item["country"] = country_item["country"] country_scrapy_item["country"] = country_item["country"]
country_scrapy_item["flag_description"] = country_item["flag_description"] country_scrapy_item["flag_description"] = country_item["flag_description"]
country_scrapy_item["anthem"] = anthem_text country_scrapy_item["anthem"] = anthem_text
country_scrapy_item["anthem_url"] = urls["anthem_page_url"]
country_scrapy_item["anthem_file_url"] = f"https://en.wikipedia.org{anthem_file_url}"
country_scrapy_item["file_urls"] = [ country_scrapy_item["file_urls"] = [
country_item["flag_image_url"], country_item["flag_image_url"],
f"https://en.wikipedia.org{anthem_file_url}", f"https://en.wikipedia.org{anthem_file_url}",

3930
playground/downloaded_data_inspection_lab/Untitled.ipynb
View File

File diff suppressed because one or more lines are too long