Compare commits

...

6 Commits

Author SHA1 Message Date
a3dbc934ed reporter 2025-12-30 18:40:37 +01:00
0f88f0c7d0 Merge remote-tracking branch 'origin/main'
# Conflicts:
#	90 test.py
2025-12-29 23:28:05 +01:00
4678d3fe7f reporter 2025-12-29 06:32:04 +01:00
b39e94a054 Merge remote-tracking branch 'origin/main' 2025-12-29 06:31:31 +01:00
e99d42fa97 Add .gitignore (PyCharm, Python cache) 2025-12-29 05:48:36 +01:00
fdba388228 reporter 2025-12-28 07:19:48 +01:00
7 changed files with 7 additions and 53 deletions

3
.idea/.gitignore generated vendored
View File

@@ -1,3 +0,0 @@
# Default ignored files
/shelf/
/workspace.xml

10
.idea/NewsGroups.iml generated
View File

@@ -1,10 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$">
<excludeFolder url="file://$MODULE_DIR$/.venv" />
</content>
<orderEntry type="jdk" jdkName="Python 3.12 (NewsGroups)" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
</module>

View File

@@ -1,16 +0,0 @@
<component name="InspectionProjectProfileManager">
<profile version="1.0">
<option name="myName" value="Project Default" />
<inspection_tool class="PyCompatibilityInspection" enabled="true" level="WARNING" enabled_by_default="true">
<option name="ourVersions">
<value>
<list size="3">
<item index="0" class="java.lang.String" itemvalue="2.7" />
<item index="1" class="java.lang.String" itemvalue="3.13" />
<item index="2" class="java.lang.String" itemvalue="3.7" />
</list>
</value>
</option>
</inspection_tool>
</profile>
</component>

View File

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

8
.idea/modules.xml generated
View File

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

6
.idea/vcs.xml generated
View File

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

View File

@@ -15,8 +15,9 @@ def sanitize(value):
# ================= CONFIG ================= # ================= CONFIG =================
GROUP = "alt.binaries.e-book.magazines" GROUP = "alt.binaries.e-book.magazines"
TOTAL_ARTICLES = 50_000_000 TOTAL_ARTICLES = 75_000_000
BATCH_SIZE = 10_000 BATCH_SIZE = 50_000
FIRST=70805000
# ========================================= # =========================================
load_dotenv() load_dotenv()
@@ -43,8 +44,10 @@ with nntplib.NNTP_SSL(
first = int(first) first = int(first)
last = int(last) last = int(last)
start_global = first # start_global = first
end_global = min(first + TOTAL_ARTICLES - 1, last) start_global = FIRST
# end_global = min(first + TOTAL_ARTICLES - 1, last)
end_global = last
print(f"🎯 Target range: {start_global} {end_global}") print(f"🎯 Target range: {start_global} {end_global}")