Skip to content
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.

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

Fix list commands #42

Merged
merged 3 commits into from
Aug 13, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion setup.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@

setup(
name="datacamp-downloader",
version="3.0",
version="3.1",
author="Mohammad Al-Fetyani",
author_email="m4bh@hotmail.com",
description="Download your completed courses on Datacamp easily!",
Expand Down
2 changes: 1 addition & 1 deletion src/datacamp_downloader/constants.py
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
LOGIN_URL = "https://www.datacamp.com/users/sign_in"
LOGIN_DETAILS_URL = "https://www.datacamp.com/api/users/signed_in"

SESSION_FILE = tempfile.gettempdir() + "/.datacamp.v2"
SESSION_FILE = tempfile.gettempdir() + "/.datacamp.v3"

PROFILE_URL = "https://www.datacamp.com/profile/{slug}"
COURSE_DETAILS_API = "https://campus-api.datacamp.com/api/courses/{id}/"
Expand Down
52 changes: 27 additions & 25 deletions src/datacamp_downloader/datacamp_utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,7 @@ def init(self):
self.has_active_subscription = False
self.loggedin = False
self.login_data = None
self.profile_data = None

self.courses = []
self.tracks = []
Expand Down Expand Up @@ -145,6 +146,16 @@ def set_token(self, token):
self.session.add_token(token)
self._set_profile()

def get_profile_data(self):
if not self.profile_data:
profile = self.session.get(PROFILE_URL.format(slug=self.login_data["slug"]))
self.session.driver.minimize_window()
soup = BeautifulSoup(profile, "html.parser")
self.profile_data = self.session.to_json(
soup.find(id="__NEXT_DATA__").string
)
return self.profile_data

@login_required
@animate_wait
def list_completed_tracks(self, refresh):
Expand All @@ -167,12 +178,13 @@ def list_completed_courses(self, refresh):
table.add_row(["ID", "Title", "Datasets", "Exercises", "Videos"])
table_so_far = table.draw()
Logger.clear_and_print(table_so_far)
for course in self.get_completed_courses(refresh):
for i, course in enumerate(self.get_completed_courses(refresh), 1):
all_exercises_count = sum([c.nb_exercises for c in course.chapters])
videos_count = sum([c.number_of_videos for c in course.chapters])
course.order = i
table.add_row(
[
course.order,
i,
course.title,
len(course.datasets),
all_exercises_count - videos_count,
Expand Down Expand Up @@ -366,23 +378,10 @@ def get_completed_tracks(self, refresh=False):

self.tracks = []

profile = self.session.get(PROFILE_URL.format(slug=self.login_data["slug"]))
self.session.driver.minimize_window()

soup = BeautifulSoup(profile, "html.parser")
tracks_title = soup.findAll("div", {"class": "track-block__main"})
tracks_link = soup.findAll(
"a", {"href": re.compile("^/tracks"), "class": "shim"}
)
for i in range(len(tracks_link)):
link = "https://www.datacamp.com" + tracks_link[i]["href"]
self.tracks.append(
Track(
f"t{i + 1}",
tracks_title[i].getText().replace("\n", " ").strip(),
link,
)
)
data = self.get_profile_data()
completed_tracks = data["props"]["pageProps"]["completed_tracks"]
for i, track in enumerate(completed_tracks, 1):
self.tracks.append(Track(f"t{i}", track["title"].strip(), track["url"]))
all_courses = set()
# add courses
for track in self.tracks:
Expand All @@ -407,11 +406,15 @@ def get_completed_courses(self, refresh=False):

self.courses = []

for course in self._get_courses_from_link(
PROFILE_URL.format(slug=self.login_data["slug"])
):
self.courses.append(course)
yield course
data = self.get_profile_data()
completed_courses = data["props"]["pageProps"]["completed_courses"]
for course in completed_courses:
fetched_course = self.get_course(course["id"])
if not fetched_course:
continue
self.session.driver.minimize_window()
self.courses.append(fetched_course)
yield fetched_course

if not self.courses:
return []
Expand Down Expand Up @@ -461,7 +464,6 @@ def _get_courses_from_link(self, link: str):
continue
course = self.get_course(int(id))
if course:
course.order = i
yield course

def _get_chapter_name(self, chapter: Chapter):
Expand Down
2 changes: 1 addition & 1 deletion src/datacamp_downloader/downloader.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
from .helper import Logger
from .templates.lang import Language

__version__ = "3.0.0"
__version__ = "3.1.0"


def version_callback(value: bool):
Expand Down
5 changes: 4 additions & 1 deletion src/datacamp_downloader/session.py
Original file line number Diff line number Diff line change
Expand Up @@ -83,9 +83,12 @@ def get(self, url):
def get_json(self, url):
page = self.get(url)
page = self.driver.find_element(By.TAG_NAME, "pre").text
parsed_json = json.loads(page)
parsed_json = self.to_json(page)
return parsed_json

def to_json(self, page: str):
return json.loads(page)

def get_element_by_id(self, id: str) -> WebElement:
return self.driver.find_element(By.ID, id)

Expand Down