diff options
| -rw-r--r-- | .gitignore | 1 | ||||
| -rw-r--r-- | python-recipe-scrapers.spec | 163 | ||||
| -rw-r--r-- | sources | 1 |
3 files changed, 165 insertions, 0 deletions
@@ -0,0 +1 @@ +/recipe_scrapers-14.36.1.tar.gz diff --git a/python-recipe-scrapers.spec b/python-recipe-scrapers.spec new file mode 100644 index 0000000..5ecd02f --- /dev/null +++ b/python-recipe-scrapers.spec @@ -0,0 +1,163 @@ +%global _empty_manifest_terminate_build 0 +Name: python-recipe-scrapers +Version: 14.36.1 +Release: 1 +Summary: Python package, scraping recipes from all over the internet +License: MIT License +URL: https://github.com/hhursev/recipe-scrapers/ +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/99/a0/082537aaeeb21ea6feff914375c12feb9e09c02b441fc7724faa3411f7fb/recipe_scrapers-14.36.1.tar.gz +BuildArch: noarch + +Requires: python3-beautifulsoup4 +Requires: python3-extruct +Requires: python3-isodate +Requires: python3-requests + +%description +A simple web scraping tool for recipe sites. + pip install recipe-scrapers +then: + from recipe_scrapers import scrape_me + scraper = scrape_me('https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/') + # Q: What if the recipe site I want to extract information from is not listed below? + # A: You can give it a try with the wild_mode option! If there is Schema/Recipe available it will work just fine. + scraper = scrape_me('https://www.feastingathome.com/tomato-risotto/', wild_mode=True) + scraper.host() + scraper.title() + scraper.total_time() + scraper.image() + scraper.ingredients() + scraper.instructions() + scraper.instructions_list() + scraper.yields() + scraper.to_json() + scraper.links() + scraper.nutrients() # if available +You also have an option to scrape html-like content + import requests + from recipe_scrapers import scrape_html + url = "https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/" + html = requests.get(url).content + scraper = scrape_html(html=html, org_url=url) + scraper.title() + scraper.total_time() + # etc... +Notes: +- ``scraper.links()`` returns a list of dictionaries containing all of the <a> tag attributes. The attribute names are the dictionary keys. + +%package -n python3-recipe-scrapers +Summary: Python package, scraping recipes from all over the internet +Provides: python-recipe-scrapers +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-recipe-scrapers +A simple web scraping tool for recipe sites. + pip install recipe-scrapers +then: + from recipe_scrapers import scrape_me + scraper = scrape_me('https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/') + # Q: What if the recipe site I want to extract information from is not listed below? + # A: You can give it a try with the wild_mode option! If there is Schema/Recipe available it will work just fine. + scraper = scrape_me('https://www.feastingathome.com/tomato-risotto/', wild_mode=True) + scraper.host() + scraper.title() + scraper.total_time() + scraper.image() + scraper.ingredients() + scraper.instructions() + scraper.instructions_list() + scraper.yields() + scraper.to_json() + scraper.links() + scraper.nutrients() # if available +You also have an option to scrape html-like content + import requests + from recipe_scrapers import scrape_html + url = "https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/" + html = requests.get(url).content + scraper = scrape_html(html=html, org_url=url) + scraper.title() + scraper.total_time() + # etc... +Notes: +- ``scraper.links()`` returns a list of dictionaries containing all of the <a> tag attributes. The attribute names are the dictionary keys. + +%package help +Summary: Development documents and examples for recipe-scrapers +Provides: python3-recipe-scrapers-doc +%description help +A simple web scraping tool for recipe sites. + pip install recipe-scrapers +then: + from recipe_scrapers import scrape_me + scraper = scrape_me('https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/') + # Q: What if the recipe site I want to extract information from is not listed below? + # A: You can give it a try with the wild_mode option! If there is Schema/Recipe available it will work just fine. + scraper = scrape_me('https://www.feastingathome.com/tomato-risotto/', wild_mode=True) + scraper.host() + scraper.title() + scraper.total_time() + scraper.image() + scraper.ingredients() + scraper.instructions() + scraper.instructions_list() + scraper.yields() + scraper.to_json() + scraper.links() + scraper.nutrients() # if available +You also have an option to scrape html-like content + import requests + from recipe_scrapers import scrape_html + url = "https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/" + html = requests.get(url).content + scraper = scrape_html(html=html, org_url=url) + scraper.title() + scraper.total_time() + # etc... +Notes: +- ``scraper.links()`` returns a list of dictionaries containing all of the <a> tag attributes. The attribute names are the dictionary keys. + +%prep +%autosetup -n recipe-scrapers-14.36.1 + +%build +%py3_build + +%install +%py3_install +install -d -m755 %{buildroot}/%{_pkgdocdir} +if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi +if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi +if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi +if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi +pushd %{buildroot} +if [ -d usr/lib ]; then + find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/lib64 ]; then + find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/bin ]; then + find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/sbin ]; then + find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst +fi +touch doclist.lst +if [ -d usr/share/man ]; then + find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst +fi +popd +mv %{buildroot}/filelist.lst . +mv %{buildroot}/doclist.lst . + +%files -n python3-recipe-scrapers -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Wed May 10 2023 Python_Bot <Python_Bot@openeuler.org> - 14.36.1-1 +- Package Spec generated @@ -0,0 +1 @@ +9b433ce3e5606ca4764951de15e5f7ec recipe_scrapers-14.36.1.tar.gz |