Compare commits

...

9 Commits

11 changed files with 173 additions and 0 deletions

2
.gitignore vendored
View File

@ -231,3 +231,5 @@ fabric.properties
# Android studio 3.1+ serialized cache file
.idea/caches/build_file_checksums.ser
# ---> Custom
.idea/deployment.xml

5
.idea/codeStyles/codeStyleConfig.xml generated Normal file
View File

@ -0,0 +1,5 @@
<component name="ProjectCodeStyleConfiguration">
<state>
<option name="PREFERRED_PROJECT_CODE_STYLE" value="Default" />
</state>
</component>

8
.idea/heiseselect-dl.iml generated Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" />
<orderEntry type="jdk" jdkName="Python 3.11 (heiseselect-dl)" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
</module>

View File

@ -0,0 +1,26 @@
<component name="InspectionProjectProfileManager">
<profile version="1.0">
<option name="myName" value="Project Default" />
<inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
<option name="ignoredPackages">
<value>
<list size="1">
<item index="0" class="java.lang.String" itemvalue="google" />
</list>
</value>
</option>
</inspection_tool>
<inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
<option name="ignoredIdentifiers">
<list>
<option value="str.decode" />
</list>
</option>
</inspection_tool>
<inspection_tool class="SpellCheckingInspection" enabled="false" level="TYPO" enabled_by_default="false">
<option name="processCode" value="true" />
<option name="processLiterals" value="true" />
<option name="processComments" value="true" />
</inspection_tool>
</profile>
</component>

View File

@ -0,0 +1,6 @@
<component name="InspectionProjectProfileManager">
<settings>
<option name="USE_PROJECT_PROFILE" value="false" />
<version value="1.0" />
</settings>
</component>

4
.idea/misc.xml generated Normal file
View File

@ -0,0 +1,4 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11 (heiseselect-dl)" project-jdk-type="Python SDK" />
</project>

8
.idea/modules.xml generated Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectModuleManager">
<modules>
<module fileurl="file://$PROJECT_DIR$/.idea/heiseselect-dl.iml" filepath="$PROJECT_DIR$/.idea/heiseselect-dl.iml" />
</modules>
</component>
</project>

6
.idea/vcs.xml generated Normal file
View File

@ -0,0 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="VcsDirectoryMappings">
<mapping directory="$PROJECT_DIR$" vcs="Git" />
</component>
</project>

79
main.py Normal file
View File

@ -0,0 +1,79 @@
import sys
import time
import requests
import logging
from rich.logging import RichHandler
FORMAT = "%(message)s"
# We're defaulting to log level WARNING for all modules
logging.basicConfig(
level="WARNING", format=FORMAT, datefmt="[%X]", handlers=[RichHandler()]
)
log = logging.getLogger("rich")
# Our own code gets its own log level, that's probably what we want to play with most
log.setLevel(logging.INFO)
# If we need to manually adjust log level for a specific module here's how you get a list of all modules that
# themselves use the 'logging' module. See also https://stackoverflow.com/a/36208664.
#for key in logging.Logger.manager.loggerDict:
# print(key)
username =
password =
dl_dir =
dl_dir = dl_dir.rstrip("\\")
file_name_on_disk = r"""2021-5.pdf"""
dl_url = r"""https://www.heise.de/select/ct/archiv/2021/5/download"""
dl_wait_timeout = 60
def logout(logged_in_session: requests.Session) -> None:
log.debug(f"Logging out ...")
with logged_in_session.get("https://www.heise.de/sso/login/logout") as logout_request:
log.debug(f"Logout got HTTP status code {logout_request.status_code}")
def login(login_username: str, login_password: str) -> requests.Session:
log.debug(f"Logging in ...")
session = requests.Session()
payload = {
"username": login_username,
"password": login_password
}
response = session.post("https://www.heise.de/sso/login/login", data=payload, allow_redirects=False)
if "Set-Cookie" in response.headers:
log.debug(f"Logged in, cookie received")
return session
def download_mag(**kwargs: requests.Session) -> None:
log.info(f"Preparing heise.de session ...")
have_printed_wait_notice = False
logged_in_session = kwargs.get("logged_in_session")
if not logged_in_session:
logged_in_session = login(username, password)
started_waiting = time.time()
log.info(f"Requesting AWS download ...")
while True:
if time.time() - started_waiting > dl_wait_timeout:
log.warning(f"We've waited {dl_wait_timeout}s for download. Exiting 1 ...")
sys.exit(1)
if int(logged_in_session.get(dl_url).headers['Content-Length']) > 1000000:
break
if not have_printed_wait_notice: log.debug(f"Waiting for heise's AWS backend ...")
have_printed_wait_notice = True
time.sleep(3)
log.info(f"Downloading ...")
with logged_in_session.get(dl_url) as dl_request:
with open(dl_dir + r"\\" + file_name_on_disk, "wb") as file:
file.write(dl_request.content)
log.info(f"Download complete")
logout(logged_in_session)
download_mag()
log.debug("Done, exiting 0 ...")
sys.exit(0)

3
requirements.in Normal file
View File

@ -0,0 +1,3 @@
requests
lxml
rich

26
requirements.txt Normal file
View File

@ -0,0 +1,26 @@
#
# This file is autogenerated by pip-compile with python 3.10
# To update, run:
#
# pip-compile
#
certifi==2021.10.8
# via requests
charset-normalizer==2.0.12
# via requests
colorama==0.4.4
# via rich
commonmark==0.9.1
# via rich
idna==3.3
# via requests
lxml==4.8.0
# via -r requirements.in
pygments==2.11.2
# via rich
requests==2.27.1
# via -r requirements.in
rich==11.2.0
# via -r requirements.in
urllib3==1.26.8
# via requests