adding screenshot script

slack-bot/geckodriver.log

@@ -0,0 +1,39 @@
+1570055118361	mozrunner::runner	INFO	Running command: "/usr/bin/firefox" "-marionette" "-foreground" "-no-remote" "-profile" "/tmp/rust_mozprofilerB4DJp"
+1570055118656	addons.webextension.screenshots@mozilla.org	WARN	Loading extension 'screenshots@mozilla.org': Reading manifest: Invalid extension permission: mozillaAddons
+1570055118656	addons.webextension.screenshots@mozilla.org	WARN	Loading extension 'screenshots@mozilla.org': Reading manifest: Invalid extension permission: resource://pdf.js/
+1570055118656	addons.webextension.screenshots@mozilla.org	WARN	Loading extension 'screenshots@mozilla.org': Reading manifest: Invalid extension permission: about:reader*
+IPDL protocol Error: Received an invalid file descriptor
+IPDL protocol Error: Received an invalid file descriptor
+1570055120485	Marionette	INFO	Listening on port 35931
+1570055120666	Marionette	WARN	TLS certificate errors will be ignored for this session
+IPDL protocol Error: Received an invalid file descriptor
+[Parent 11866, Gecko_IOThread] WARNING: pipe error (68): Connection reset by peer: file /builddir/build/BUILD/firefox-66.0.2/ipc/chromium/src/chrome/common/ipc_channel_posix.cc, line 357
+1570055124259	Marionette	INFO	Stopped listening on port 35931
+1570055140941	mozrunner::runner	INFO	Running command: "/usr/bin/firefox" "-marionette" "-foreground" "-no-remote" "-profile" "/tmp/rust_mozprofileC5m1OE"
+1570055141207	addons.webextension.screenshots@mozilla.org	WARN	Loading extension 'screenshots@mozilla.org': Reading manifest: Invalid extension permission: mozillaAddons
+1570055141207	addons.webextension.screenshots@mozilla.org	WARN	Loading extension 'screenshots@mozilla.org': Reading manifest: Invalid extension permission: resource://pdf.js/
+1570055141207	addons.webextension.screenshots@mozilla.org	WARN	Loading extension 'screenshots@mozilla.org': Reading manifest: Invalid extension permission: about:reader*
+IPDL protocol Error: Received an invalid file descriptor
+IPDL protocol Error: Received an invalid file descriptor
+1570055141995	Marionette	INFO	Listening on port 39457
+1570055142049	Marionette	WARN	TLS certificate errors will be ignored for this session
+IPDL protocol Error: Received an invalid file descriptor
+[Parent 12493, Gecko_IOThread] WARNING: pipe error (71): Connection reset by peer: file /builddir/build/BUILD/firefox-66.0.2/ipc/chromium/src/chrome/common/ipc_channel_posix.cc, line 357
+[Parent 12493, Gecko_IOThread] WARNING: pipe error (80): Connection reset by peer: file /builddir/build/BUILD/firefox-66.0.2/ipc/chromium/src/chrome/common/ipc_channel_posix.cc, line 357
+1570055146451	Marionette	INFO	Stopped listening on port 39457
+1570055159366	mozrunner::runner	INFO	Running command: "/usr/bin/firefox" "-marionette" "-foreground" "-no-remote" "-profile" "/tmp/rust_mozprofileJGgS47"
+1570055159635	addons.webextension.screenshots@mozilla.org	WARN	Loading extension 'screenshots@mozilla.org': Reading manifest: Invalid extension permission: mozillaAddons
+1570055159635	addons.webextension.screenshots@mozilla.org	WARN	Loading extension 'screenshots@mozilla.org': Reading manifest: Invalid extension permission: resource://pdf.js/
+1570055159635	addons.webextension.screenshots@mozilla.org	WARN	Loading extension 'screenshots@mozilla.org': Reading manifest: Invalid extension permission: about:reader*
+IPDL protocol Error: Received an invalid file descriptor
+IPDL protocol Error: Received an invalid file descriptor
+1570055160384	Marionette	INFO	Listening on port 41419
+1570055160477	Marionette	WARN	TLS certificate errors will be ignored for this session
+IPDL protocol Error: Received an invalid file descriptor
+1570055162449	Marionette	INFO	Stopped listening on port 41419
+
+###!!! [Parent][DispatchAsyncMessage] Error: PClientSource::Msg_Teardown Route error: message sent to unknown actor ID
+
+
+###!!! [Parent][RunMessage] Error: Channel closing: too late to send/recv, messages will be lost
+

slack-bot/regex.txt

@@ -1,2 +1,4 @@
 col 4
 ^\<[a-zA-Z\/]+\>(.+?)\s+?\:\s+?(.+?)\<[a-zA-Z\/]+\>(.+?)\s+?\:\s+?(.+?)\<[a-zA-Z\/]+\>(.+?)\s+?\:\s+?(.+?)\<[a-zA-Z\/]+\>(.+?)\s+?\:\s+?(.+?)\<[a-zA-Z\/]+\>(.+?)\s+?\:\s+?(.+?)\<[a-zA-Z\/]+\>$
+
+^\<td\>((.+?)\s+?\:\s+(.+?).+)<\/td\>$

slack-bot/scraper.py

@@ -2,6 +2,7 @@ from bs4 import BeautifulSoup
 from selenium import webdriver
 import emoji
 from datetime import datetime
+import re
 
 url = 'http://www.trafficengland.com/traffic-alerts'
 # prepare the  option for the chrome driver
@@ -9,7 +10,7 @@ options = webdriver.ChromeOptions()
 options.add_argument('headless')
 
 # start the chrome driver
-browser = webdriver.Chrome(chrome_options=options)
+browser = webdriver.Chrome(options=options)
 browser.get(url)
 html = browser.page_source
 
@@ -28,16 +29,16 @@ list = []
 for item in table:
     list.append(item)
 
-for i in range(0, 4):
-    print(list[i])
+# for i in range(0, 4):
+#     print(list[i])
 
-printBreak()
+# printBreak()
 
-totalItems = int(len(list) / 4)
+# totalItems = int(len(list) / 4)
 
-for i in range(0, 4):
-    print(list[i].string)
-    printBreak()
+# for i in range(0, 4):
+#     print(list[i].string)
+#     printBreak()
 
 newList = ([x.text for x in soup.find_all('td')])
 
@@ -47,8 +48,24 @@ print(emoji.emojize('Did someone say M62 :anguished:!? Let'
                     '\'s check the latest updates from Highways'
                     ' England! :police_car::rotating_light:',
                     use_aliases=True))
-print(f'As of {currentTime}, there is currently a {newList[2]} {newList[1]}'
+print(f'As of {currentTime}, there is currently {newList[2]} {newList[1]}'
       f' on the {newList[0]}')
 
 # print(list[3].prettify())
-print(str(list[3]))
+desc = str(list[3])
+descSplit = desc.split('<')
+
+pattern = r"\>(.+?)\s+?\:\s+?(.+?)$"
+
+for item in descSplit:
+    # print(item)
+    regex = re.findall(pattern, item)
+    # print(f'Type: {type(regex)}')
+    # print(f'Matches: {regex}')
+    try:
+        printBreak()
+        print(f'itemOne: {regex[0][0]}')
+        print(f'itemTwo: {regex[0][1]}')
+    except IndexError:
+        pass
+    # print(f'itemTwo: {regex[1]}')

slack-bot/screenshot.py

@@ -0,0 +1,6 @@
+from selenium import webdriver
+
+driver = webdriver.Firefox()
+driver.get('https://www.python.org')
+driver.save_screenshot('screenshot.png')
+driver.quit()

slack-bot/screenshotFull.py

@@ -0,0 +1,26 @@
+# https://stackoverflow.com/questions/41721734/take-screenshot-of-full-page-with-selenium-python-with-chromedriver/57338909#57338909
+
+from selenium import webdriver
+from PIL import Image
+
+URL = 'https://www.trafficdelays.co.uk/m62-traffic-delays/'
+
+options = webdriver.ChromeOptions()
+options.headless = True
+
+driver = webdriver.Chrome(options=options)
+driver.get(URL)
+
+S = lambda X: driver.execute_script('return document.body.parentNode.scroll'
+                                    + X)
+# driver.set_window_size(S('Width'), S('Height')+500)  # May need manual adjustment
+driver.set_window_size(S('Width'), 1000)  # May need manual adjustment
+driver.find_element_by_tag_name('body').screenshot('web_screenshot.png')
+# driver.find_element_by_css_selector('#post-4706').screenshot('web_screenshot.png')
+print(driver.find_element_by_css_selector('#post-4706').text)
+
+im = Image.open('web_screenshot.png')
+width, height = im.size
+region = im.crop((0, 0, width, 880))
+region.save('cropped.png')
+driver.quit()