From e5f17991e412b94705179c6908c5e8b747269b7d Mon Sep 17 00:00:00 2001 From: CoprDistGit Date: Fri, 5 May 2023 05:13:40 +0000 Subject: automatic import of python-robobrowser --- .gitignore | 1 + python-robobrowser.spec | 384 ++++++++++++++++++++++++++++++++++++++++++++++++ sources | 1 + 3 files changed, 386 insertions(+) create mode 100644 python-robobrowser.spec create mode 100644 sources diff --git a/.gitignore b/.gitignore index e69de29..90f98f2 100644 --- a/.gitignore +++ b/.gitignore @@ -0,0 +1 @@ +/robobrowser-0.5.3.tar.gz diff --git a/python-robobrowser.spec b/python-robobrowser.spec new file mode 100644 index 0000000..6c8f4b2 --- /dev/null +++ b/python-robobrowser.spec @@ -0,0 +1,384 @@ +%global _empty_manifest_terminate_build 0 +Name: python-robobrowser +Version: 0.5.3 +Release: 1 +Summary: Your friendly neighborhood web scraper +License: MIT +URL: https://github.com/jmcarp/robobrowser +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/f3/53/fd527e78fe8bdf7ec24b3b821c88c2dcbbe63d120c838f80f12ed0a0fac6/robobrowser-0.5.3.tar.gz +BuildArch: noarch + + +%description +Homepage: `http://robobrowser.readthedocs.org/ `_ +RoboBrowser is a simple, Pythonic library for browsing the web without a standalone web browser. RoboBrowser +can fetch a page, click on links and buttons, and fill out and submit forms. If you need to interact with web services +that don't have APIs, RoboBrowser can help. + import re + from robobrowser import RoboBrowser + # Browse to Genius + browser = RoboBrowser(history=True) + browser.open('http://genius.com/') + # Search for Porcupine Tree + form = browser.get_form(action='/search') + form # + form['q'].value = 'porcupine tree' + browser.submit_form(form) + # Look up the first song + songs = browser.select('.song_link') + browser.follow_link(songs[0]) + lyrics = browser.select('.lyrics') + lyrics[0].text # \nHear the sound of music ... + # Back to results page + browser.back() + # Look up my favorite song + song_link = browser.get_link('trains') + browser.follow_link(song_link) + # Can also search HTML using regex patterns + lyrics = browser.find(class_=re.compile(r'\blyrics\b')) + lyrics.text # \nTrain set and match spied under the blind... +RoboBrowser combines the best of two excellent Python libraries: +`Requests `_ and +`BeautifulSoup `_. +RoboBrowser represents browser sessions using Requests and HTML responses +using BeautifulSoup, transparently exposing methods of both libraries: + import re + from robobrowser import RoboBrowser + browser = RoboBrowser(user_agent='a python robot') + browser.open('https://github.com/') + # Inspect the browser session + browser.session.cookies['_gh_sess'] # BAh7Bzo... + browser.session.headers['User-Agent'] # a python robot + # Search the parsed HTML + browser.select('div.teaser-icon') # [
+ # + #
, + # ... + browser.find(class_=re.compile(r'column', re.I)) #
+ #
+ # + # ... +You can also pass a custom `Session` instance for lower-level configuration: + from requests import Session + from robobrowser import RoboBrowser + session = Session() + session.verify = False # Skip SSL verification + session.proxies = {'http': 'http://custom.proxy.com/'} # Set default proxies + browser = RoboBrowser(session=session) +RoboBrowser also includes tools for working with forms, inspired by +`WebTest `_ and `Mechanize `_. + from robobrowser import RoboBrowser + browser = RoboBrowser() + browser.open('http://twitter.com') + # Get the signup form + signup_form = browser.get_form(class_='signup') + signup_form # + form['vehicle'] # + # Checked values can be get and set like lists + form['vehicle'].options # [u'Bike', u'Car'] + form['vehicle'].value # [] + form['vehicle'].value = ['Bike'] + form['vehicle'].value = ['Bike', 'Car'] + # Values can also be set using input labels + form['vehicle'].labels # [u'I have a bike', u'I have a car \r\n'] + form['vehicle'].value = ['I have a bike'] + form['vehicle'].value # [u'Bike'] + # Only values that correspond to checkbox values or labels can be set; + # this will raise a `ValueError` + form['vehicle'].value = ['Hot Dogs'] +Uploading files: + from robobrowser import RoboBrowser + # Browse to a page with an upload form + browser = RoboBrowser() + browser.open('http://cgi-lib.berkeley.edu/ex/fup.html') + # Find the form + upload_form = browser.get_form() + upload_form # + # Choose a file to upload + upload_form['upfile'] # + upload_form['upfile'].value = open('path/to/file.txt', 'r') + # Submit + browser.submit(upload_form) +By default, creating a browser instantiates a new requests `Session`. + +%package -n python3-robobrowser +Summary: Your friendly neighborhood web scraper +Provides: python-robobrowser +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-robobrowser +Homepage: `http://robobrowser.readthedocs.org/ `_ +RoboBrowser is a simple, Pythonic library for browsing the web without a standalone web browser. RoboBrowser +can fetch a page, click on links and buttons, and fill out and submit forms. If you need to interact with web services +that don't have APIs, RoboBrowser can help. + import re + from robobrowser import RoboBrowser + # Browse to Genius + browser = RoboBrowser(history=True) + browser.open('http://genius.com/') + # Search for Porcupine Tree + form = browser.get_form(action='/search') + form # + form['q'].value = 'porcupine tree' + browser.submit_form(form) + # Look up the first song + songs = browser.select('.song_link') + browser.follow_link(songs[0]) + lyrics = browser.select('.lyrics') + lyrics[0].text # \nHear the sound of music ... + # Back to results page + browser.back() + # Look up my favorite song + song_link = browser.get_link('trains') + browser.follow_link(song_link) + # Can also search HTML using regex patterns + lyrics = browser.find(class_=re.compile(r'\blyrics\b')) + lyrics.text # \nTrain set and match spied under the blind... +RoboBrowser combines the best of two excellent Python libraries: +`Requests `_ and +`BeautifulSoup `_. +RoboBrowser represents browser sessions using Requests and HTML responses +using BeautifulSoup, transparently exposing methods of both libraries: + import re + from robobrowser import RoboBrowser + browser = RoboBrowser(user_agent='a python robot') + browser.open('https://github.com/') + # Inspect the browser session + browser.session.cookies['_gh_sess'] # BAh7Bzo... + browser.session.headers['User-Agent'] # a python robot + # Search the parsed HTML + browser.select('div.teaser-icon') # [
+ # + #
, + # ... + browser.find(class_=re.compile(r'column', re.I)) #
+ #
+ # + # ... +You can also pass a custom `Session` instance for lower-level configuration: + from requests import Session + from robobrowser import RoboBrowser + session = Session() + session.verify = False # Skip SSL verification + session.proxies = {'http': 'http://custom.proxy.com/'} # Set default proxies + browser = RoboBrowser(session=session) +RoboBrowser also includes tools for working with forms, inspired by +`WebTest `_ and `Mechanize `_. + from robobrowser import RoboBrowser + browser = RoboBrowser() + browser.open('http://twitter.com') + # Get the signup form + signup_form = browser.get_form(class_='signup') + signup_form # + form['vehicle'] # + # Checked values can be get and set like lists + form['vehicle'].options # [u'Bike', u'Car'] + form['vehicle'].value # [] + form['vehicle'].value = ['Bike'] + form['vehicle'].value = ['Bike', 'Car'] + # Values can also be set using input labels + form['vehicle'].labels # [u'I have a bike', u'I have a car \r\n'] + form['vehicle'].value = ['I have a bike'] + form['vehicle'].value # [u'Bike'] + # Only values that correspond to checkbox values or labels can be set; + # this will raise a `ValueError` + form['vehicle'].value = ['Hot Dogs'] +Uploading files: + from robobrowser import RoboBrowser + # Browse to a page with an upload form + browser = RoboBrowser() + browser.open('http://cgi-lib.berkeley.edu/ex/fup.html') + # Find the form + upload_form = browser.get_form() + upload_form # + # Choose a file to upload + upload_form['upfile'] # + upload_form['upfile'].value = open('path/to/file.txt', 'r') + # Submit + browser.submit(upload_form) +By default, creating a browser instantiates a new requests `Session`. + +%package help +Summary: Development documents and examples for robobrowser +Provides: python3-robobrowser-doc +%description help +Homepage: `http://robobrowser.readthedocs.org/ `_ +RoboBrowser is a simple, Pythonic library for browsing the web without a standalone web browser. RoboBrowser +can fetch a page, click on links and buttons, and fill out and submit forms. If you need to interact with web services +that don't have APIs, RoboBrowser can help. + import re + from robobrowser import RoboBrowser + # Browse to Genius + browser = RoboBrowser(history=True) + browser.open('http://genius.com/') + # Search for Porcupine Tree + form = browser.get_form(action='/search') + form # + form['q'].value = 'porcupine tree' + browser.submit_form(form) + # Look up the first song + songs = browser.select('.song_link') + browser.follow_link(songs[0]) + lyrics = browser.select('.lyrics') + lyrics[0].text # \nHear the sound of music ... + # Back to results page + browser.back() + # Look up my favorite song + song_link = browser.get_link('trains') + browser.follow_link(song_link) + # Can also search HTML using regex patterns + lyrics = browser.find(class_=re.compile(r'\blyrics\b')) + lyrics.text # \nTrain set and match spied under the blind... +RoboBrowser combines the best of two excellent Python libraries: +`Requests `_ and +`BeautifulSoup `_. +RoboBrowser represents browser sessions using Requests and HTML responses +using BeautifulSoup, transparently exposing methods of both libraries: + import re + from robobrowser import RoboBrowser + browser = RoboBrowser(user_agent='a python robot') + browser.open('https://github.com/') + # Inspect the browser session + browser.session.cookies['_gh_sess'] # BAh7Bzo... + browser.session.headers['User-Agent'] # a python robot + # Search the parsed HTML + browser.select('div.teaser-icon') # [
+ # + #
, + # ... + browser.find(class_=re.compile(r'column', re.I)) #
+ #
+ # + # ... +You can also pass a custom `Session` instance for lower-level configuration: + from requests import Session + from robobrowser import RoboBrowser + session = Session() + session.verify = False # Skip SSL verification + session.proxies = {'http': 'http://custom.proxy.com/'} # Set default proxies + browser = RoboBrowser(session=session) +RoboBrowser also includes tools for working with forms, inspired by +`WebTest `_ and `Mechanize `_. + from robobrowser import RoboBrowser + browser = RoboBrowser() + browser.open('http://twitter.com') + # Get the signup form + signup_form = browser.get_form(class_='signup') + signup_form # + form['vehicle'] # + # Checked values can be get and set like lists + form['vehicle'].options # [u'Bike', u'Car'] + form['vehicle'].value # [] + form['vehicle'].value = ['Bike'] + form['vehicle'].value = ['Bike', 'Car'] + # Values can also be set using input labels + form['vehicle'].labels # [u'I have a bike', u'I have a car \r\n'] + form['vehicle'].value = ['I have a bike'] + form['vehicle'].value # [u'Bike'] + # Only values that correspond to checkbox values or labels can be set; + # this will raise a `ValueError` + form['vehicle'].value = ['Hot Dogs'] +Uploading files: + from robobrowser import RoboBrowser + # Browse to a page with an upload form + browser = RoboBrowser() + browser.open('http://cgi-lib.berkeley.edu/ex/fup.html') + # Find the form + upload_form = browser.get_form() + upload_form # + # Choose a file to upload + upload_form['upfile'] # + upload_form['upfile'].value = open('path/to/file.txt', 'r') + # Submit + browser.submit(upload_form) +By default, creating a browser instantiates a new requests `Session`. + +%prep +%autosetup -n robobrowser-0.5.3 + +%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-robobrowser -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Fri May 05 2023 Python_Bot - 0.5.3-1 +- Package Spec generated diff --git a/sources b/sources new file mode 100644 index 0000000..9a199d7 --- /dev/null +++ b/sources @@ -0,0 +1 @@ +333ad401f4a0b320fa873c78bc5fb64d robobrowser-0.5.3.tar.gz -- cgit v1.2.3