Script to ban authors from Google Groups
Wanderer
wanderer at dialup4less.com
Mon Jul 3 09:30:05 EDT 2017
I use this script to ban authors from Google Groups. You need to create a banned authors text file with each author separated by a new line. For Mozilla you need to compile it to a pyc file, associate pyc files with Python and create a bookmark. You then use the bookmark to enter google groups web page.
# remove banned author and authors with mostly caps
# to compile to pyc
#>>>import py_compile
#>>>py_compile.compile("file.py")
import urllib2
import webbrowser
import os
from bs4 import BeautifulSoup
PALEMOON = 'Mozilla/5.0 (Windows NT 6.1; WOW64) KHTML/4.11 Gecko/20130308 Firefox/33.0 (PaleMoon/25.2)'
WATERFOX = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:40.0) Gecko/20100101 Firefox/51.1.0 Waterfox/51.1.0'
USERAGENTBASE = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:40.0) Gecko/20100101 '
BROWSERPATH = 'C:\\"Program Files"\\Waterfox\\waterfox.exe'
FILENAME = 'C:\\PyStuff\\pygroup.htm'
WEBPAGE = "https://groups.google.com/forum/?_escaped_fragment_=forum/comp.lang.python%5B1-50%5D"
BANNED_AUTHORS_FILE = 'C:\\PyStuff\\bannedAuthors.txt'
def getUserAgentVersion():
""" get the useragent version
returns agentVersion
-- user agent version in format Firefox/51.0.1 Waterfox/51.0.1
"""
bvers = os.popen(BROWSERPATH + " -v").read()
bversList = bvers.split()
agentVersion = 'Firefox/' + bversList[2] + ' ' + bversList[1] + '/' + bversList[2]
return agentVersion
def getwebpage(url):
""" Open a webpage
url -- the url to the webpage
returns
page -- the source for the webpage
"""
user_agent = USERAGENTBASE + getUserAgentVersion()
headers = { 'User-Agent' : user_agent }
req = urllib2.Request(url, None, headers)
response = urllib2.urlopen(req)
page = response.read()
return page
def getBannedAuthors():
""" Convert the banned authors text file into a list
returns
bannedAuthors -- list of banned author strings
"""
f = open(BANNED_AUTHORS_FILE, 'r')
bannedAuthors = f.read().split('\n')
f.close()
return bannedAuthors
def removeBadAuthors(html_doc):
""" Remove posts from google group by authors that are mostly caps or on the Banned List
html_doc -- an html document
"""
bannedAuthors = getBannedAuthors()
print bannedAuthors
soup = BeautifulSoup(html_doc)
#print soup.prettify()
post = soup.find("tr")
while post is not None:
author = post.find("td", "author")
aname = author.get_text()
if author is None:
print "Author is None"
oldpost = post
post = oldpost.find_next_sibling('tr')
oldpost.decompose()
elif aname in bannedAuthors:
print "Author is Banned"
oldpost = post
post = oldpost.find_next_sibling('tr')
oldpost.decompose()
else:
print author
numCaps = 1.0 * sum(1 for c in aname if c.isupper())
ratio = numCaps/(1.0*len(aname))
print ratio
oldpost = post
post = oldpost.find_next_sibling('tr')
if ratio > 0.7:
oldpost.decompose()
print "BIG"
if post is None: print "Post is NONE"
f = open(FILENAME, 'w')
f.write(soup.prettify().encode('ascii', 'ignore'))
f.close()
def main():
html_doc = getwebpage(WEBPAGE)
removeBadAuthors(html_doc)
webbrowser.open(FILENAME)
print 'done'
if __name__ == "__main__":
main()
More information about the Python-list
mailing list