Daily-Dose/main.py

187 lines
4.3 KiB
Python
Raw Normal View History

2020-11-10 13:26:35 +00:00
import configparser
from datetime import date
import feedparser
from mdutils import MdUtils
markdown = True
2020-11-10 13:30:02 +00:00
pdf = False
html = True
2020-11-10 13:26:35 +00:00
html_stylesheet = "styles/simple.css"
title_animation = "fade-down"
heading_animation = "fade-right"
list_animation = "fade-left"
if (pdf and not markdown) or (html and not markdown):
print("Markdown should be True to convert to pdf/html")
debug = False
ConvertToHTML = True
title = date.today().strftime('%d %B, %Y')
feeds = configparser.ConfigParser()
if feeds.read("feeds.ini") == []:
print("feeds.ini does not exist!")
exit(1)
else:
if debug:
print("Reading feeds.ini")
feeds.read("feeds.ini")
rss_feeds = [x for x in feeds.keys()]
rss_feeds.pop(0)
if debug:
print("Read %s feeds from the configuration file" % str(len(rss_feeds)))
def GetPosts(feed):
Posts = {}
ToIgnore = []
ReadSummary = True
URL = None
ToRead = 5
try:
URL = feeds[feed]["URL"]
except KeyError:
print("Improper configuration for %s. No URL Specified")
exit(1)
try:
ToIgnore = eval(feeds[feed]["IGNORE"])
except KeyError:
None
try:
ReadSummary = eval(feeds[feed]["SUMMARY"])
except KeyError:
ReadSummary = True
try:
ToRead = eval(feeds[feed]["ToRead"])
except:
None
rss = feedparser.parse(URL)
maximum = len(rss.entries)
count = 0
if ToRead == -1 or ToRead > maximum:
ToRead = maximum
posts = []
summaries = []
while count != ToRead:
Skip = False
Title = str(rss.entries[count].title)
Summary = rss.entries[count].summary
for words in ToIgnore:
if (words.lower() in Title.lower()) or (words.lower() in Summary.lower()):
Skip = True
break
if not Skip:
posts.append(Title)
if ReadSummary:
summaries.append(Summary)
count += 1
for idx in range(len(posts)):
Posts[idx] = {}
Posts[idx]["post"] = {}
Posts[idx]["post"]["title"] = posts[idx].encode('utf-8')
if ReadSummary:
Posts[idx]["post"]["summary"] = summaries[idx].encode('utf-8')
else:
Posts[idx]["summary"] = None
Posts["NoOfPosts"] = len(posts)
Posts["Summary"] = ReadSummary
return Posts
posts = {}
for feed in rss_feeds:
sauce = GetPosts(feed)
posts[feed] = sauce
#print(posts)
if markdown:
mdfile = MdUtils(file_name=title,title='Daily Dose')
for feed in posts:
mdfile.new_header(level=1,title="From %s" % feed)
for idx in range(posts[feed]["NoOfPosts"]):
mdfile.write(str("* **"+posts[feed][idx]["post"]["title"].decode('utf-8'))+"**")
if posts[feed]["Summary"]:
mdfile.write(" - ")
mdfile.write(posts[feed][idx]["post"]["summary"].decode('utf-8'))
mdfile.write("\n\n")
else:
mdfile.write("\n")
mdfile.new_line("\n")
mdfile.new_table_of_contents(table_title='Contents', depth=2)
mdfile.create_md_file()
import pypandoc
if pdf:
ifname = str(title.strip()) + ".md"
ofname = str(title.strip()) + ".pdf"
args = ['-V', 'geometry:margin=1.5cm']
convert = pypandoc.convert_file(ifname, 'pdf', outputfile=ofname,extra_args=args)
if html:
from bs4 import BeautifulSoup
ifname = str(title.strip()) + ".md"
2020-11-10 13:30:02 +00:00
ofname = str(title.strip()) + ".html"
2020-11-10 13:26:35 +00:00
convert = pypandoc.convert_file(ifname,'html5',outputfile=ofname,extra_args=['-s'])
assert(convert) == ''
2020-11-10 13:30:02 +00:00
with open(ofname) as fp:
soup = BeautifulSoup(fp,'html5lib')
2020-11-10 13:26:35 +00:00
2020-11-10 13:30:02 +00:00
aos_css = soup.new_tag('link',href='https://unpkg.com/aos@2.3.1/dist/aos.css',rel='stylesheet')
soup.head.append(aos_css)
2020-11-10 13:26:35 +00:00
2020-11-10 13:30:02 +00:00
font = soup.new_tag('link',href=html_stylesheet,rel='stylesheet')
soup.head.append(font)
2020-11-10 13:26:35 +00:00
2020-11-10 13:30:02 +00:00
title = soup.new_tag('title')
title.string = "DailyDose"
soup.head.append(title)
2020-11-10 13:26:35 +00:00
2020-11-10 13:30:02 +00:00
aos_js = soup.new_tag('script',src="https://unpkg.com/aos@2.3.1/dist/aos.js")
soup.head.append(aos_js)
2020-11-10 13:26:35 +00:00
2020-11-10 13:30:02 +00:00
aos_script = soup.new_tag('script')
aos_script.string = "AOS.init();"
2020-11-10 13:26:35 +00:00
2020-11-10 13:30:02 +00:00
soup.body.append(aos_script)
2020-11-10 13:26:35 +00:00
2020-11-10 13:30:02 +00:00
for feed in rss_feeds:
ToFindID = str("from-"+str(feed.strip().replace(":","").replace(" ","-").lower()))
ToEdit = soup.find("h1", {"id": ToFindID})
ToEdit['data-aos'] = 'fade-right'
2020-11-10 13:26:35 +00:00
2020-11-10 13:30:02 +00:00
soup.find("h1",{"id":"daily-dose"})['data-aos'] = title_animation
soup.find("h1",{"id":"contents"})['data-aos'] = heading_animation
2020-11-10 13:26:35 +00:00
2020-11-10 13:30:02 +00:00
paragraphs = soup.find_all("p")
for paras in paragraphs:
paras['data-aos'] = list_animation
2020-11-10 13:26:35 +00:00
2020-11-10 13:30:02 +00:00
lis = soup.find_all("li")
for li in lis:
if li.a == None:
li['data-aos'] = list_animation
2020-11-10 13:26:35 +00:00
2020-11-10 13:30:02 +00:00
with open(ofname, "w") as outf:
2020-11-10 13:26:35 +00:00
outf.write(str(soup))