Skip to content

Added covers, fixed getting all torrents #39

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lnxx-56 wants to merge 10 commits into
base: master
Choose a base branch
from
Open

Added covers, fixed getting all torrents #39

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
bf55919
Added covers, fixed getting all torrent
lnxx-56 Oct 18, 2024
3f5212d
Fixed poster regexp
lnxx-56 Oct 19, 2024
f112df3
Bumped version to 2.2.0
Oct 25, 2024
8b189e8
fixed infinit loop when no search pattern defined
lnxx-56 Nov 1, 2024
cf1456c
fixed infinit loop & poster img
Nov 5, 2024
de73cba
reformatted ncoreparser/parser.py
lnxx-56 Nov 7, 2024
db1ad8d
fixed torrent details page poster regex
lnxx-56 Nov 7, 2024
19f6df2
fixed return value when number is none
lnxx-56 Nov 7, 2024
ea65f23
added poster imgs to tests
lnxx-56 Nov 7, 2024
c4328f6
Update ncoreparser/client.py
lnxx-56 Feb 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions ncoreparser/client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,7 @@ def search(self, pattern, type=SearchParamType.ALL_OWN, where=SearchParamWhere.N
sort_by=ParamSort.UPLOAD, sort_order=ParamSeq.DECREASING, number=None):
page_count = 1
torrents = []
while number is None or len(torrents) < number:
while number is in (None, -1) or len(torrents) < number:
url = URLs.DOWNLOAD_PATTERN.value.format(page=page_count,
t_type=type.value,
sort=sort_by.value,
Expand All @@ -79,9 +79,9 @@ def search(self, pattern, type=SearchParamType.ALL_OWN, where=SearchParamWhere.N
except Exception as e:
raise NcoreConnectionError(f"Error while searhing torrents. {e}") from e
new_torrents = [Torrent(**params) for params in self._page_parser.get_items(request.text)]
torrents.extend(new_torrents)
if number is None or len(new_torrents) == 0:
return torrents
torrents.extend(new_torrents)
page_count += 1
return torrents[:number]

Expand Down
4 changes: 2 additions & 2 deletions ncoreparser/client_async.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,7 @@ async def search(self, pattern, type=SearchParamType.ALL_OWN, where=SearchParamW
sort_by=ParamSort.UPLOAD, sort_order=ParamSeq.DECREASING, number=None):
page_count = 1
torrents = []
while number is None or len(torrents) < number:
while number is None or number == -1 or len(torrents) < number:
Copy link
Owner

@radaron radaron Nov 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

same

url = URLs.DOWNLOAD_PATTERN.value.format(page=page_count,
t_type=type.value,
sort=sort_by.value,
Expand All @@ -81,9 +81,9 @@ async def search(self, pattern, type=SearchParamType.ALL_OWN, where=SearchParamW
except Exception as e:
raise NcoreConnectionError(f"Error while searhing torrents. {e}") from e
new_torrents = [Torrent(**params) for params in self._page_parser.get_items(request.text)]
torrents.extend(new_torrents)
if number is None or len(new_torrents) == 0:
return torrents
torrents.extend(new_torrents)
page_count += 1
return torrents[:number]

Expand Down
40 changes: 34 additions & 6 deletions ncoreparser/parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,13 +9,18 @@ class TorrentsPageParser:
def __init__(self):
self.type_pattern = re.compile(r'<a href=".*\/torrents\.php\?tipus=(.*?)">'
r'<img src=".*" class="categ_link" alt=".*" title=".*">')
self.id_name_pattern = re.compile(r'<a href=".*?" onclick="torrent\(([0-9]+)\); return false;" title="(.*?)">')
self.id_name_poster_pattern = re.compile(
Copy link
Owner

@radaron radaron Nov 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I recommend to use simpler regex here. As I see there is the image tag:

<img onmouseout="elrejt('borito3814785')" onmouseover="mutat('https://nc-img.cdn.l7cache.com/covers/L9_kjpbQ9UwZFlXZ?28795815', '281', 'borito3814785', this)" border="0" src="data:image/gif;base64,R0lGODlhDwAPAJEAAAAAAP///////wAAACH5BAEAAAIALAAAAAAPAA8AAAINlI+py+0Po5y02otnAQA7" class="infobar_ico">

And here you could parse out the torrent id: elrejt('borito3814785') the id is: 3814785.

Copy link
Owner

@radaron radaron Nov 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Then you can iterate over the ids. check is the id in this pattern output. If yes add if not set no cover.

r'<a href=".*?" onclick="torrent\((\d+)\);.*?" title="(.*?)">.*?(?:onmouseover="mutat\(\'(https:\/\/.*?)\',.*?)',
re.DOTALL
)
self.id_name_patter = re.compile(r'<a href=".*?" onclick="torrent\(([0-9]+)\); return false;" title="(.*?)">')
Copy link
Owner

@radaron radaron Nov 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

typo: pattern

self.date_pattern = re.compile(r'<div class="box_feltoltve2">(.*?)<br>(.*?)</div>')
self.size_pattern = re.compile(r'<div class="box_meret2">(.*?)</div>')
self.not_found_pattern = re.compile(r'<div class="lista_mini_error">Nincs találat!</div>')
self.seeders_pattern = re.compile(r'<div class="box_s2"><a class="torrent" href=".*">([0-9]+)</a></div>')
self.leechers_pattern = re.compile(r'<div class="box_l2"><a class="torrent" href=".*">([0-9]+)</a></div>')


@staticmethod
def get_key(data):
key_pattern = r'<link rel="alternate" href=".*?\/rss.php\?key=(?P<key>[a-z,0-9]+)" title=".*"'
Expand All @@ -25,24 +30,43 @@ def get_key(data):
raise NcoreParserError(f"Error while read user "
f"key with pattern: {key_pattern}")


def id_exists(self, data, search_id):
Copy link
Owner

@radaron radaron Nov 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It can be staticmethod and can start with _

for i, id in enumerate(data):
if search_id in data[i]:
return True

return False


def get_items(self, data):
types = self.type_pattern.findall(data)
ids_names = self.id_name_pattern.findall(data)
ids_names_posters = self.id_name_poster_pattern.findall(data)
ids_names = self.id_name_patter.findall(data)
dates_times = self.date_pattern.findall(data)
sizes = self.size_pattern.findall(data)
seed = self.seeders_pattern.findall(data)
leech = self.leechers_pattern.findall(data)
if len(types) != 0 and len(types) == len(ids_names) == \
Copy link
Owner

@radaron radaron Nov 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You can create a poster dict here, where the key is the torrent id and the value is the poster url or "no cover".
You can iterate on IDs, and add the id to this dict key, then find the poster image and add as value.

For this I recommend to convert the re.findall response to a dictionary:
https://www.geeksforgeeks.org/python-convert-a-list-of-tuples-into-dictionary/


# Not all torrents has poster img
if (len(ids_names) != len(ids_names_posters)):
for i, id in enumerate(ids_names):
if not self.id_exists(ids_names_posters, ids_names[i][0]):
missing_torrent_data = (ids_names[i][0], ids_names[i][1], 'no cover')
Copy link
Owner

@radaron radaron Nov 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The no Cover could be a constant. Because in one place no cover in another No cover

Copy link
Owner

@radaron radaron Nov 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

in data.py you can create a NO_COVER constant and use here.

ids_names_posters.append(missing_torrent_data)

if len(types) != 0 and len(types) == len(ids_names_posters) == \
len(dates_times) == len(sizes) == len(seed) == len(leech):
ids, names = zip(*ids_names)
ids, names, poster_image = zip(*ids_names_posters)
dates, times = zip(*dates_times)
key = self.get_key(data)
else:
if not self.not_found_pattern.search(data):
raise NcoreParserError(f"Error while parse download items in {self.__class__.__name__}.")
return
Copy link
Owner

@radaron radaron Nov 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This return hides an error. If the len of found data is not equal.

for i, id in enumerate(ids):
yield {"id": id, "title": names[i], "key": key, "date": parse_datetime(dates[i], times[i]),
"size": Size(sizes[i]), "type": SearchParamType(types[i]), "seed": seed[i], "leech": leech[i]}
"size": Size(sizes[i]), "type": SearchParamType(types[i]), "seed": seed[i], "leech": leech[i], "poster_image": poster_image[i]}


class TorrenDetailParser:
Expand All @@ -57,6 +81,7 @@ def __init__(self):
self.peers_pattern = re.compile(r'div class="dt">Seederek:</div>.*?<div class="dd"><a onclick=".*?">'
r'(?P<seed>[0-9]+)</a></div>.*?<div class="dt">Leecherek:</div>.*?<div '
r'class="dd"><a onclick=".*?">(?P<leech>[0-9]+)</a></div>', re.DOTALL)
self.poster_image_pattern = re.compile(r'<td class="inforbar_img" align="center"><img\s+[^>]*src="(https://[^\"]+)', re.DOTALL)

def get_item(self, data):
try:
Expand All @@ -69,9 +94,12 @@ def get_item(self, data):
peers = self.peers_pattern.search(data)
seed = peers.group('seed')
leech = peers.group('leech')
poster_image_match = self.poster_image_pattern.search(data)
poster_image = poster_image_match.group(1) if poster_image_match else "No cover"

except AttributeError as e:
raise NcoreParserError(f"Error while parsing by detailed page. {e}") from e
return {"title": title, "key": key, "date": date, "size": size, "type": t_type, 'seed': seed, 'leech': leech}
return {"title": title, "key": key, "date": date, "size": size, "type": t_type, 'seed': seed, 'leech': leech, 'poster_image': poster_image}


class RssParser:
Expand Down
3 changes: 2 additions & 1 deletion ncoreparser/torrent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

class Torrent:
def __init__(self, id, title, key, size, #pylint: disable=too-many-arguments
type, date, seed, leech, **params): #pylint: disable=too-many-arguments
type, date, seed, leech, poster_image, **params): #pylint: disable=too-many-arguments
self._details = {}
self._details["id"] = int(id)
self._details["title"] = title
Expand All @@ -14,6 +14,7 @@ def __init__(self, id, title, key, size, #pylint: disable=too-many-arguments
self._details["date"] = date
self._details["seed"] = seed
self._details["leech"] = leech
self._details["poster_image"] = poster_image
self._details["download"] = URLs.DOWNLOAD_LINK.value.format(id=id, key=key)
self._details.update(params)

Expand Down
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ build-backend = "hatchling.build"

[project]
name = "ncoreparser"
version = "2.1.2"
version = "2.2.0"
description = "Package to download from ncore.pro"
authors = [
{ name="Aron Radics", email="aron.radics.jozsef@gmail.com" }
Expand Down
27 changes: 19 additions & 8 deletions tests/manual.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,21 +5,22 @@

def print_category(msg):
print("")
print("*{:175}*".format("-" * 175))
print(f"|{msg:^175}|")
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10))
print("|{:^100}|{:^30}|{:^10}|{:^10}|{:^10}|{:^10}|".format("Title", "Type", "Size", "ID", "Seed", "Leech"))
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10))
print("*{:276}*".format("-" * 276))
print(f"|{msg:^276}|")
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*{:^100}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10, "-" * 100))
print("|{:^100}|{:^30}|{:^10}|{:^10}|{:^10}|{:^10}|{:^100}|".format("Title", "Type", "Size", "ID", "Seed", "Leech", "Poster"))
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*{:^100}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10, "-" * 100))


def pretty_print(torrent):
print("|{:^100}|{:^30}|{:^10}|{:^10}|{:^10}|{:^10}|".format(torrent['title'],
print("|{:^100}|{:^30}|{:^10}|{:^10}|{:^10}|{:^10}|{:^100}|".format(torrent['title'],
torrent['type'],
str(torrent['size']),
str(torrent['id']),
torrent['seed'],
torrent['leech']))
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10))
torrent['leech'],
torrent['poster_image']))
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*{:^100}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10, "-" * 100))


parser = argparse.ArgumentParser()
Expand Down Expand Up @@ -65,6 +66,16 @@ def pretty_print(torrent):
for torrent in torrents:
pretty_print(torrent)

print_category("Test number=None")
torrents = client.search(pattern="")
for torrent in torrents:
pretty_print(torrent)

print_category("Test number=-1")
torrents = client.search(pattern="creed", number=-1)
for torrent in torrents:
pretty_print(torrent)

client.logout()
end = time.time()

Expand Down
27 changes: 19 additions & 8 deletions tests/manual_async.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,21 +6,22 @@

def print_category(msg):
print("")
print("*{:175}*".format("-" * 175))
print(f"|{msg:^175}|")
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10))
print("|{:^100}|{:^30}|{:^10}|{:^10}|{:^10}|{:^10}|".format("Title", "Type", "Size", "ID", "Seed", "Leech"))
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10))
print("*{:276}*".format("-" * 276))
print(f"|{msg:^276}|")
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*{:^100}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10, "-" * 100))
print("|{:^100}|{:^30}|{:^10}|{:^10}|{:^10}|{:^10}|{:^100}|".format("Title", "Type", "Size", "ID", "Seed", "Leech", "Poster"))
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*{:^100}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10, "-" * 100))


def pretty_print(torrent):
print("|{:^100}|{:^30}|{:^10}|{:^10}|{:^10}|{:^10}|".format(torrent['title'],
print("|{:^100}|{:^30}|{:^10}|{:^10}|{:^10}|{:^10}|{:^100}|".format(torrent['title'],
torrent['type'],
str(torrent['size']),
str(torrent['id']),
torrent['seed'],
torrent['leech']))
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10))
torrent['leech'],
torrent['poster_image']))
print("*{:^100}*{:^30}*{:^10}*{:^10}*{:^10}*{:^10}*{:^100}*".format("-" * 100, "-" * 30, "-" * 10, "-" * 10, "-" * 10, "-" * 10, "-" * 100))


parser = argparse.ArgumentParser()
Expand Down Expand Up @@ -65,6 +66,16 @@ async def main():
for torrent in torrents:
pretty_print(torrent)

print_category("Test number=None")
torrents = await client.search(pattern="")
for torrent in torrents:
pretty_print(torrent)

print_category("Test number=-1")
torrents = await client.search(pattern="creed", number=-1)
for torrent in torrents:
pretty_print(torrent)

await client.logout()
end = time.time()

Expand Down