initial commit

1 files changed, 78 insertions, 0 deletions

diff --git a/fetch-issue-webpages.py b/fetch-issue-webpages.py
new file mode 100755
index 0000000..86d6b71
--- /dev/null
+++ b/fetch-issue-webpages.py
@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+# Startdate: 2020-05-29 16:22
+# History:
+# Usage:
+#    ln -s issues.all.web_url output/files-to-fetch.txt
+#    ./fetch-issues-webpages.py
+# How to make this work:
+#    apt-get install python3-pyvirtualdisplay
+#    download this geckodriver, place in /usr/local/bin
+# References:
+#    basic guide https://web.archive.org/web/20191031110759/http://scraping.pro/use-headless-firefox-scraping-linux/
+#    https://stackoverflow.com/questions/40302006/no-such-file-or-directory-geckodriver-for-a-python-simple-selenium-applicatio
+#    geckodriver https://github.com/mozilla/geckodriver/releases/download/v0.24.0/geckodriver-v0.24.0-linux64.tar.gz
+#    https://www.selenium.dev/selenium/docs/api/py/index.html?highlight=get
+#    page source https://www.selenium.dev/selenium/docs/api/py/webdriver_remote/selenium.webdriver.remote.webdriver.html?highlight=title#selenium.webdriver.remote.webdriver.WebDriver.title
+#    make sure all comments load https://stackoverflow.com/questions/26566799/wait-until-page-is-loaded-with-selenium-webdriver-for-python/44998503#44998503
+#    https://crossbrowsertesting.com/blog/test-automation/automate-login-with-selenium/
+# Improve:
+from pyvirtualdisplay import Display
+from selenium import webdriver
+from selenium.webdriver.support.ui import WebDriverWait
+import re, time, getpass
+
+def ask_password(prompt):
+    #return input(prompt+": ")
+    return getpass.getpass(prompt+": ")
+
+def scrollDown(driver, value):
+   driver.execute_script("window.scrollBy(0,"+str(value)+")")
+
+# Scroll down the page
+def scrollDownAllTheWay(driver):
+   old_page = driver.page_source
+   while True:
+      #logging.debug("Scrolling loop")
+      for i in range(2):
+         scrollDown(driver, 500)
+         time.sleep(2)
+      new_page = driver.page_source
+      if new_page != old_page:
+         old_page = new_page
+      else:
+         break
+   return True
+
+server_string="https://git.devuan.org"
+outdir="/mnt/public/www/issues"
+
+with open("output/files-to-fetch.txt") as f:
+   lines=[line.rstrip() for line in f]
+
+# ask password now instead of after the delay
+password = ask_password("Enter password for "+server_string)
+
+display = Display(visible=0, size=(800, 600))
+display.start()
+
+browser = webdriver.Firefox()
+
+# log in to gitlab instance
+browser.get(server_string+"/users/sign_in")
+browser.find_element_by_id("user_login").send_keys('bgstack15')
+browser.find_element_by_id("user_password").send_keys(password)
+browser.find_element_by_class_name("qa-sign-in-button").click()
+browser.get(server_string+"/profile") # always needs the authentication
+scrollDownAllTheWay(browser)
+
+for thisfile in lines:
+   destfile=re.sub("\.+",".",re.sub("\/|issues",".",re.sub("^"+re.escape(server_string)+"\/","",thisfile)))+".html"
+   print("Saving",thisfile,outdir+"/"+destfile)
+   browser.get(thisfile)
+   scrollDownAllTheWay(browser)
+   with open(outdir+"/"+destfile,"w") as text_file:
+      print(browser.page_source.encode('utf-8'),file=text_file)
+
+# done with loop
+browser.quit()
+display.stop()