[WIP] Lastin Egor

FinalTaskEgorLastin.py

@@ -0,0 +1,86 @@
+import feedparser
+import argparse
+
+def parseRSS( rss_url ):
+    return feedparser.parse( rss_url )
+
+def getTimes(rss_url):
+    times=[]
+    feed=parseRSS(rss_url)
+    for newsitem in feed['items']:
+        times.append(newsitem['published'])
+        return times
+
+def getLinks(rss_url):
+    links=[]
+    feed=  parseRSS(rss_url)
+    for newsitem in feed['items']:
+        links.append(newsitem[ 'link'])
+    return links
+
+#def getTimes( rs_url)
+def getHeadlines( rss_url ):
+    headlines = []
+    feed = parseRSS( rss_url )
+    for newsitem in feed['items']:
+        headlines.append(newsitem['title'])
+    return headlines
+
+# A list to hold all headlines,links,.....
+
+allheadlines=[]
+alllinks=[]
+alltimes=[]
+allpics=[]
+
+# List of RSS feeds that we will fetch and combine
+newsurls = {'yahoonews':        'http://news.yahoo.com/rss/'}
+# Iterate over the feed urls
+for key,url in newsurls.items():
+    print(key,url)
+    # Call getHeadlines() and combine the returned headlines with allheadlines
+    allheadlines.extend( getHeadlines( url ) )
+    alllinks.extend( getLinks(url ))
+    alltimes.extend( getTimes( url))
+    res = "\n".join("Link:    {}\nTitle:       {}\nTime published:        {}\n".format( x, y, z) for  x, y, z in zip(alllinks, allheadlines, alltimes))
+# Iterate over the allheadlines list and print each headline
+for i in res:
+    print(i)
+    #print(ln,"\n",hl.replace("'","'"))
+
+#
+#
+#
+"""
+import feedparser
+import webbrowser
+import argparse
+parser = argparse.ArgumentParser(description='This is the python-built RSS reader.')
+parser.add_argument('-u','--ur',action='store',dest='url',default=None,help='<Required> url link',required=True)
+results = parser.parse_args()#output from all of this
+feed = feedparser.parse(results.url)
+feed_entries = feed.entries
+
+def parseRSS(feed):
+    return feedparser.parse(feed)#used
+def getHeadlines( results.url ):
+    headlines = []
+    feed = parseRSS(results.url)
+    for newsitem in feed['items']:
+        headlines.append(newsitem['title'])
+
+    return headlines
+
+allheadlines = []
+
+for key,url in newsurls.items():
+#
+    allheadlines.extend(getHeadlines(url))
+#
+for hl in allheadlines:
+    print(hl.replace("&#39;","'"))
+
+def formatEntry(headline,date,link):
+	print(1)
+"""
+

PKG-INFO

@@ -0,0 +1,10 @@
+Metadata-Version: 1.0
+Name: RSS-READER.py
+Version: 0.1
+Summary: UNKNOWN
+Home-page: UNKNOWN
+Author: UNKNOWN
+Author-email: UNKNOWN
+License: UNKNOWN
+Description: UNKNOWN
+Platform: UNKNOWN

SOURCES.txt

@@ -0,0 +1,7 @@
+finalTaskPart1.py
+setup.py
+RSS_READER.py.egg-info/PKG-INFO
+RSS_READER.py.egg-info/SOURCES.txt
+RSS_READER.py.egg-info/dependency_links.txt
+RSS_READER.py.egg-info/requires.txt
+RSS_READER.py.egg-info/top_level.txt

dependency_links.txt

@@ -0,0 +1 @@
+

finalTask part3.py

@@ -0,0 +1,123 @@
+import feedparser
+import argparse
+import json
+import requests
+import datetime
+import base64
+"""import section"""
+
+
+version = 0.1
+parser = argparse.ArgumentParser()
+parser.add_argument("URL", help="This is the full adress of the rss feed.use ' ' ")
+parser.add_argument("-l", "--lim", help="outputs the latest X articles. can be run without lim to get all articles")
+parser.add_argument("-o", "--output", help="outputs news to file", action="store_true")
+parser.add_argument("-j", "--json", help="outputs a jsonDump", action="store_true")
+parser.add_argument("-d", "--dl", help="downloads data.makes a file as date right now", action="store_true")
+parser.add_argument("-r", help="reads the dl version of the feed. arg is the date of dl, you dont need a working url")
+#parser.add_argument("--pdf", help="converts the output to the specified format (.pdf) ")
+#parser.add_argument("--html", help="converts the output to the specified format (.html) ")
+args = parser.parse_args()
+limit = args.lim
+
+
+def captureFeed(URL):
+    """Gets a feed fo everything to use"""
+    feed = feedparser.parse(args.URL)
+    return feed
+
+
+def fileOutput():
+    """Outputs a json dump of feed.entries to a file that is called "news.txt".works """
+    open("news.txt", "w").close()
+    feed = captureFeed(args.URL)
+    f = open("news.txt", "w+")
+    input1 = json.dumps(feed.entries)
+    f.write(input1)
+    f.close()
+
+
+def standardOutput():
+    """This is what happens when there are no tail commands added"""
+    if not args.r:
+        feed = captureFeed(args.URL)
+    else:
+        remoteFeed = remoteRead()
+        feed = remoteFeed
+    for article in feed.entries:
+        print("Title:  ", article.title.replace("'", "'"), "\nDate:   ",
+              article.published, "\nLinks:  ", article.link, "\n")
+
+def jsonOutput():
+    """Outputs a json Dump to the console"""
+    feed = captureFeed(args.URL)
+    print(json.dumps(feed.entries))
+
+
+def limitedOutput(limit):
+    if not args.r:
+        feed = captureFeed(args.URL)
+    else:
+        remoteFeed = remoteRead()
+        feed = remoteFeed
+    try:
+        for Index in range(int(limit)):
+            T = str(feed.entries[Index].title)
+            P = feed.entries[Index].published
+            L = feed.entries[Index].link
+            print("Title:  ", T.replace("'", "'"), "\nDate:   ",
+                  P, "\nLinks:  ", L, "\n")
+        print("your limit was: ", limit)
+    except IndexError:
+        print("no")
+    """Output if the user uses the --limit args, protected by indexError"""
+
+
+def cacheDate(URL):
+    response = requests.get(URL)
+    today = datetime.date.today()
+    dateNow = today.strftime("%d-%m-%Y")
+    filename = dateNow + ".xml"
+    with open(filename, 'wb') as file:
+        file.write(response.content)
+
+
+def remoteRead():
+    remoteFeed = feedparser.parse(args.r)
+    return remoteFeed
+
+
+def getPics():
+    feed = captureFeed(args.URL)
+    listOfPics = []
+    try:
+        for i in range(len(feed.entries)-1):
+            pics = feed.entries[i].media_content[0].get('url')
+            listOfPics.append(pics)
+    except IndexError:
+        print("not all posts have images")
+    print(listOfPics)
+
+getPics()        
+if limit and not args.r:
+    limitedOutput(limit)
+elif args.json:
+    jsonOutput()
+elif not limit and not args.r:
+    standardOutput()
+
+if args.r and not limit:
+    remoteRead()
+if limit and args.r:
+    limitedOutput(limit)
+
+
+if args.dl:
+    cacheDate(args.URL)
+
+
+
+if args.output:
+    feed = captureFeed(args.URL)
+    fileOutput()
+    """Has to go away from the global score. could try to put it into a main()"""

finalTaskPart1.py

@@ -0,0 +1,50 @@
+import feedparser
+import argparse
+import gc
+
+
+version = 0.1
+parser = argparse.ArgumentParser()
+parser.add_argument("URL", help="This is the full adress of the rss feed.use ' ' ")
+parser.add_argument("-l", "--lim", help="outputs the latest X(int)articles. can be run without lim to get all articles")
+args = parser.parse_args()
+limit=args.lim
+
+def captureFeed(url):
+    feed = feedparser.parse(args.URL)
+    return feed
+
+
+def standardOutput():
+    """This is what happens when there are no tail commands added"""
+    feed = captureFeed(args.URL)
+    for article in feed.entries:
+        print("Title:  ", article.title.replace("'", "'"), "\nDate:   ",
+              article.published, "\nLinks:  ", article.link, "\n")
+
+
+def limitedOutput(limit):
+    """This is what happens when there is only  parameter on limmit"""
+    feed = captureFeed(args.URL)
+    for i in range(int(limit)):
+        T=feed.entries[i].title
+        P=feed.entries[i].published
+        L=feed.entries[i].link
+        print("Title:  ", T.replace("'", "'"), "\nDate:   ",
+              P, "\nLinks:  ", L, "\n")
+    print("your limit was: ",limit)
+
+
+if limit:
+    limitedOutput(limit)
+else:
+    standardOutput()
+
+
+"""
+I have created the bare minimal working rss reader.
+It has 2 parameters other than help. LIMIT and URL. i will include more as time progresses.
+I need to remove logic from the global scope. i have done most of it but i want to use a class
+for this,yet I dont know enough about them yet as I was ill on the date of the lecture and the powerpoint was complex for me at this stage
+setuptools havent been made yet, Ill try to make them now
+"""

k.py

@@ -0,0 +1,90 @@
+import feedparser
+import argparse
+import json
+"""import section"""
+
+version = 0.1
+parser = argparse.ArgumentParser()
+parser.add_argument("URL", help="This is the full adress of the rss feed.use ' ' ")
+parser.add_argument("-l", "--lim", help="outputs the latest X articles. can be run without lim to get all articles")
+parser.add_argument("-o", "--output", help="outputs news to file", action="store_true")
+parser.add_argument("-j", "--json", help="outputs a jsonDump", action="store_true")
+parser.add_argument("-d","-date", help="caches the data and makes a file named by the time right now")
+parser.add_argument("-c","--con", help="converts the output to some specified format like .pdf and .html")
+args = parser.parse_args()
+limit = args.lim
+"""ALL MUST GO. I might try to pull an if __main__()"""
+
+
+def cacheDate():
+    print("a")
+
+
+def captureFeed(URL):
+    """Gets a feed fo everything to use"""
+    feed = feedparser.parse(args.URL)
+    return feed
+
+
+def fileOutput():
+    """Outputs a json dump of feed.entries to a file that is called "news.txt".works """
+    open("news.txt", "w").close()
+    feed = captureFeed(args.URL)
+    f = open("news.txt", "w+")
+    input1 = json.dumps(feed.entries)
+    f.write(input1)
+    f.close()
+
+
+def standardOutput():
+    """This is what happens when there are no tail commands added"""
+    feed = captureFeed(args.URL)
+    for article in feed.entries:
+        print("Title:  ", article.title.replace("'", "'"), "\nDate:   ",
+              article.published, "\nLinks:  ", article.link, "\n")
+
+
+def jsonOutput():
+    """Outputs a json Dump to the console"""
+    feed = captureFeed(args.URL)
+    print(json.dumps(feed.entries))
+
+
+def limitedOutput(limit):
+    feed = captureFeed(args.URL)
+    try:
+        for Index in range(int(limit)):
+            T = str(feed.entries[Index].title)
+            P = feed.entries[Index].published
+            L = feed.entries[Index].link
+            print("Title:  ", T.replace("'", "'"), "\nDate:   ",
+                  P, "\nLinks:  ", L, "\n")
+        print("your limit was: ", limit)
+    except IndexError:
+        print("no")
+    """Output if the user uses the --limit args, protected by indexError"""
+
+
+if limit:
+    limitedOutput(limit)
+elif args.json:
+    jsonOutput()
+else:
+    standardOutput()
+
+if args.output:
+    feed = captureFeed(args.URL)
+    fileOutput()
+    """Has to go away from the global score. could try to put it into a main()"""
+
+"""
+I have created the bare minimal working rss reader.
+It has 2 parameters other than help. LIMIT and URL.
+I will include more as time progresses.
+I need to remove logic from the global scope.
+I have done most of it but i want to use a class
+for this,yet I dont know enough about them yet as I
+was ill on the date of the lecture and the powerpoint
+was complex for me at this stage
+setuptools havent been made yet, Ill try to make them now
+"""

requires.txt

@@ -0,0 +1 @@
+feedparser

setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

setup.py

@@ -0,0 +1,8 @@
+from setuptools import setup, find_packages
+setup(
+    name="RSS-READER.py",
+    version="0.1",
+    packages=find_packages(include=["feedparser","feedparser.*"]),
+    scripts=["finalTaskPart1.py"],
+    install_requires=['feedparser']
+)

top_level.txt

@@ -0,0 +1 @@
+