lynnesbian/FediBooks
lynnesbian/FediBooks
1
0
Fork 0
mirror of https://github.com/Lynnesbian/FediBooks/ synced 2024-11-25 08:38:59 +00:00
Code Issues Releases Wiki Activity

fixed indentation issue, hopefully #21 is fixed now

Browse source
This commit is contained in:
Lynne Megido 2019-09-17 18:12:32 +10:00
parent 386d32367a
commit 5d35519818
1 changed files with 48 additions and 48 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

96
scrape.py
View file

@ -41,55 +41,55 @@ def scrape_posts(account):
r = requests.get(uri) r = requests.get(uri)
j = r.json() j = r.json()
# here we go! # here we go!
# warning: scraping posts from outbox.json is messy stuff # warning: scraping posts from outbox.json is messy stuff
done = False done = False
while not done and len(j['orderedItems']) > 0: while not done and len(j['orderedItems']) > 0:
for oi in j['orderedItems']: for oi in j['orderedItems']:
if oi['type'] == "Create": if oi['type'] == "Create":
# this is a status/post/toot/florp/whatever # this is a status/post/toot/florp/whatever
# first, check to see if we already have this in the database # first, check to see if we already have this in the database
post_id = re.search(r"([^\/]+)/?$", oi['object']['id']).group(1) # extract 123 from https://example.com/posts/123/ post_id = re.search(r"([^\/]+)/?$", oi['object']['id']).group(1) # extract 123 from https://example.com/posts/123/
c.execute("SELECT COUNT(*) FROM `posts` WHERE `fedi_id` = %s AND `post_id` = %s", (handle, post_id)) c.execute("SELECT COUNT(*) FROM `posts` WHERE `fedi_id` = %s AND `post_id` = %s", (handle, post_id))
count = c.fetchone() count = c.fetchone()
if count is not None and int(count[0]) > 0: if count is not None and int(count[0]) > 0:
# this post is already in the DB. # this post is already in the DB.
# we'll set done to true because we've caught up to where we were last time. # we'll set done to true because we've caught up to where we were last time.
done = True
# we'll still iterate over the rest of the posts, though, in case there are still some new ones on this page.
continue
content = oi['object']['content']
# remove HTML tags and such from post
content = functions.extract_post(content)
if len(content) > 65535:
# post is too long to go into the DB
continue
try:
c.execute("INSERT INTO `posts` (`fedi_id`, `post_id`, `content`, `cw`) VALUES (%s, %s, %s, %s)", (
handle,
post_id,
content,
1 if (oi['object']['summary'] != None and oi['object']['summary'] != "") else 0
))
except:
#TODO: error handling
raise
if not done:
if pleroma:
r = requests.get(j['next'], timeout = 10)
else:
r = requests.get(j['prev'], timeout = 10)
if r.status_code == 429:
# we are now being ratelimited, move on to the next user
print("Hit rate limit while scraping {}".format(handle))
done = True done = True
else: # we'll still iterate over the rest of the posts, though, in case there are still some new ones on this page.
j = r.json() continue
content = oi['object']['content']
# remove HTML tags and such from post
content = functions.extract_post(content)
if len(content) > 65535:
# post is too long to go into the DB
continue
try:
c.execute("INSERT INTO `posts` (`fedi_id`, `post_id`, `content`, `cw`) VALUES (%s, %s, %s, %s)", (
handle,
post_id,
content,
1 if (oi['object']['summary'] != None and oi['object']['summary'] != "") else 0
))
except:
#TODO: error handling
raise
if not done:
if pleroma:
r = requests.get(j['next'], timeout = 10)
else:
r = requests.get(j['prev'], timeout = 10)
if r.status_code == 429:
# we are now being ratelimited, move on to the next user
print("Hit rate limit while scraping {}".format(handle))
done = True
else:
j = r.json()
db.commit() db.commit()