death916/c2cscrape
1
0
Fork 0
mirror of https://github.com/Death916/c2cscrape.git synced 2026-04-10 03:04:40 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Revert "reset url to base each cycle since were not trying to get all past episodes currently"

Browse source 
This reverts commit 1a1eec98ce.
This commit is contained in:
Death916 2025-02-26 02:39:59 -08:00
parent 1a1eec98ce
commit adae4689a3
1 changed files with 4 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

13
src/c2cscrape.py
View file

@ -9,8 +9,7 @@ import random
class C2CScrape:
def __init__(self):
self.base_url = 'https://zfirelight.blogspot.com/'
self.current_url = self.base_url
self.url = 'https://zfirelight.blogspot.com/'
self.episodes = []
self.last_download = None
self.last_download_link = None
@ -136,7 +135,7 @@ class C2CScrape:
def process_episode(self):
try:
drive_url = self.get_drive_link(self.current_url) # This sets self.soup
drive_url = self.get_drive_link(self.url) # This sets self.soup
if not drive_url:
return
@ -161,21 +160,17 @@ class C2CScrape:
try:
# Run our core operations
self.current_url = self.base_url
self.process_episode()
self.get_older_posts()
print(f'Episodes downloaded: {self.episodes_downloaded}')
finally:
# Ensure timer restarts even if there's an error
print("waiting 12 hours")
self.episodes_downloaded = 0
self.last_download = None
threading.Timer(43200, self.timer).start() # 43200 sec = 12 hours
# navigate to older posts button 5 times and get last 5 episodes with no repeats/ span id is blog-pager-older-link
def get_older_posts(self, limit=5):
try:
response = requests.get(self.current_url, headers=self.headers)
response = requests.get(self.url, headers=self.headers)
soup = BeautifulSoup(response.text, 'html.parser')
older_posts = soup.find('span', id='blog-pager-older-link')
processed_urls = set()
@ -189,7 +184,7 @@ class C2CScrape:
processed_urls.add(older_link)
# Get the older posts page
self.current_url = older_link # Update URL to use existing functions
self.url = older_link # Update URL to use existing functions
print(f'Processing page: {older_link}')
# Use existing process_episode method