diff --git a/01_scrapy/wikipedia_country_scraper/wikipedia_country_scraper/spiders/countrydownloader.py b/01_scrapy/wikipedia_country_scraper/wikipedia_country_scraper/spiders/countrydownloader.py index 1f35d1c..a58577d 100644 --- a/01_scrapy/wikipedia_country_scraper/wikipedia_country_scraper/spiders/countrydownloader.py +++ b/01_scrapy/wikipedia_country_scraper/wikipedia_country_scraper/spiders/countrydownloader.py @@ -23,8 +23,8 @@ class CountrydownloaderSpider(scrapy.Spider): "//table[contains(@class, 'sortable') and contains(@class, 'wikitable')]/tbody/tr[not(contains(@style, 'background'))]/td[1 and contains(@style, 'vertical-align:top;')]/b/a/@href" ).getall() - # for url in country_urls_xpath: - for url in country_urls_xpath[:3]: + for url in country_urls_xpath: + # for url in country_urls_xpath[:3]: regex_match = re.search(r"\/wiki\/(?P[^$]*)", url) yield scrapy.Request( url=f"https://en.wikipedia.org{url}",