blob: b4a311e075e53f957c32864aad931312a3ada039 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
# Based on this work : https://dvenkatsagar.github.io/tutorials/python/2015/10/26/ddlv/
# The standard library modules
import os
import sys
import re
import sys
from urllib.parse import unquote
# The BeautifulSoup module
from bs4 import BeautifulSoup
# The selenium module
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
if len(sys.argv) != 2:
print("Usage:")
print(" "+str(sys.argv[0]+" <url>"))
sys.exit()
url = sys.argv[1]
print("Starting...")
driver = webdriver.Firefox()
# Load the feedly search page
driver.get("https://feedly.com/i/discover/sources/search/feed/"+url)
print("Searching...")
# Wait some crappy javascript is loaded
try:
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.CLASS_NAME, "item-header")))
except:
print("Timeout: 5 seconds, nothing found")
driver.close()
sys.exit()
# Find the link and go to the feed page information to find the correct feed link
driver.find_element_by_css_selector("a.item-header").click()
parser = BeautifulSoup(driver.page_source,"lxml")
# Get the only title who have an data-uri who is the feed link
for title in parser.find_all('h1'):
if "data-uri" in title.attrs:
data_uri = re.sub('^feed%2F', '', title.attrs["data-uri"].split("/")[1])
# Transform %2F to human readble char and print it
print("Found: "+str(unquote(data_uri)))
driver.close()
|
