Skip to content

Commit

Permalink
Update entries for November
Browse files Browse the repository at this point in the history
  • Loading branch information
@sdht0
sdht0 committed Nov 1, 2021
1 parent 8d7e7bc commit 1950d6b
Show file tree
Hide file tree
Showing 18 changed files with 40,141 additions and 37 deletions.
74 changes: 37 additions & 37 deletions Automate.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 3,
"id": "2f4c1ab9-5cd0-4524-850a-3a133d3c6c95",
"metadata": {},
"outputs": [],
Expand All @@ -34,13 +34,13 @@
"# Necessary: A correct map from the DBLP IDs to the DSG website Node IDs. This is maintained in the `dblp_to_web_mappings.txt` file.\n",
"# When needed: Selenium can also be used to mass update existing entries. Adapt from the code for adding new entries.\n",
"\n",
"working_date = \"2021.10.01\" # Set to the date the entries are being updated on.\n",
"previous_date = \"2021.09.07\" # Set to the date the entries were last updated. This is usually the last `working_date` from above, or the most recent date in the `archive` folder."
"working_date = \"2021.11.01\" # Set to the date the entries are being updated on.\n",
"previous_date = \"2021.10.01\" # Set to the date the entries were last updated. This is usually the last `working_date` from above, or the most recent date in the `archive` folder."
]
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 4,
"id": "2893840d-cdff-4f26-9bcb-cbbf1e799efd",
"metadata": {},
"outputs": [],
Expand Down Expand Up @@ -150,7 +150,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 5,
"id": "02fe688c-6051-41b1-84a0-e4bdd2d8c930",
"metadata": {},
"outputs": [],
Expand All @@ -160,6 +160,7 @@
"if not os.path.exists(authors_path):\n",
" os.makedirs(authors_path)\n",
"for author in authors_list:\n",
" print(\"Downloading for\",author)\n",
" req = urllib.request.Request(\"https://dblp.uni-trier.de/pid/%s.bib?param=1\" % author[1])\n",
" response = urllib.request.urlopen(req)\n",
" content = response.read()\n",
Expand All @@ -169,61 +170,61 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 6,
"id": "a61fdb26-cabf-458c-b3ba-09c7707d473e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Working date = 2021.10.01\n",
"Working date = 2021.11.01\n",
"len(CharlieClarke) = 218\n",
"len(GordonVCormack) = 129\n",
"len(GordonVCormack) = 130\n",
"len(KhuzaimaDaudjee) = 57\n",
"len(LukaszGolab) = 131\n",
"len(MauraGrossman) = 33\n",
"len(MauraGrossman) = 34\n",
"len(XiHe) = 31\n",
"len(IhabFIlyas) = 142\n",
"len(JimmyLin) = 447\n",
"len(JimmyLin) = 450\n",
"len(TamerOzsu) = 287\n",
"len(KennethSalem) = 91\n",
"len(SemihSalihoglu) = 50\n",
"len(MarkDSmucker) = 74\n",
"len(DavidToman) = 126\n",
"len(FrankTompa) = 89\n",
"len(GrantWeddell) = 90\n",
"total entries = 1995, deduplicated and filtered entries = 1687\n",
"article 544\n",
"total entries = 2000, deduplicated and filtered entries = 1691\n",
"article 548\n",
"inproceedings 1077\n",
"incollection 49\n",
"book 14\n",
"phdthesis 3\n",
"total = 1687\n",
"total = 1691\n",
"\n",
"Working date = 2021.09.07\n",
"len(CharlieClarke) = 216\n",
"Working date = 2021.10.01\n",
"len(CharlieClarke) = 218\n",
"len(GordonVCormack) = 129\n",
"len(KhuzaimaDaudjee) = 56\n",
"len(KhuzaimaDaudjee) = 57\n",
"len(LukaszGolab) = 131\n",
"len(MauraGrossman) = 33\n",
"len(XiHe) = 31\n",
"len(IhabFIlyas) = 142\n",
"len(JimmyLin) = 443\n",
"len(TamerOzsu) = 286\n",
"len(JimmyLin) = 447\n",
"len(TamerOzsu) = 287\n",
"len(KennethSalem) = 91\n",
"len(SemihSalihoglu) = 49\n",
"len(SemihSalihoglu) = 50\n",
"len(MarkDSmucker) = 74\n",
"len(DavidToman) = 125\n",
"len(FrankTompa) = 88\n",
"len(GrantWeddell) = 89\n",
"total entries = 1983, deduplicated and filtered entries = 1678\n",
"article 540\n",
"inproceedings 1072\n",
"len(DavidToman) = 126\n",
"len(FrankTompa) = 89\n",
"len(GrantWeddell) = 90\n",
"total entries = 1995, deduplicated and filtered entries = 1687\n",
"article 544\n",
"inproceedings 1077\n",
"incollection 49\n",
"book 14\n",
"phdthesis 3\n",
"total = 1678\n"
"total = 1687\n"
]
}
],
Expand All @@ -244,9 +245,8 @@
"name": "stdout",
"output_type": "stream",
"text": [
"New = 9 Deleted = 0\n",
"article 4\n",
"inproceedings 5\n"
"New = 4 Deleted = 0\n",
"article 4\n"
]
}
],
Expand All @@ -272,7 +272,7 @@
},
{
"cell_type": "code",
"execution_count": 24,
"execution_count": 8,
"id": "2661a3bc-20b9-41a6-8e00-75c3e6b6b184",
"metadata": {
"scrolled": true,
Expand Down Expand Up @@ -302,7 +302,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 10,
"id": "35cd6385-c401-475f-a2bb-db2d9816a726",
"metadata": {},
"outputs": [],
Expand Down Expand Up @@ -809,15 +809,15 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 11,
"id": "710d51ff-b272-4f0b-8c63-00b2919b3d81",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"9\n"
"4\n"
]
}
],
Expand Down Expand Up @@ -885,7 +885,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 12,
"id": "4413e38c-ee55-4e88-ac66-3f5eb147dd80",
"metadata": {
"tags": []
Expand All @@ -911,7 +911,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 13,
"id": "8d117232-66ab-4bbb-90f8-3adbdd56fbb6",
"metadata": {},
"outputs": [],
Expand All @@ -929,14 +929,14 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": 14,
"id": "ca73dd03-119d-4be7-b5a7-7a80424ea806",
"metadata": {},
"outputs": [],
"source": [
"# Set the correct values:\n",
"driver_path = \"/home/sdh/Downloads/installations/chromedriver\" # Chromium driver path, downloaded and extracted from https://chromedriver.chromium.org/downloads\n",
"cookie_value = \"xbTugRnz4pCDMnDz7KU4F-Pr3lvwp8jrMIcfO7NpUys\" # Login to 'My Workbench' and copy the cookie value of key 'SSESSc2214f6938283aa908e28c4bfa176f5b'\n",
"cookie_value = \"RyLKUE5ZgrerBYUQK4WULIcnz5l3u793aR2Hgxu5tNc\" # Login to 'My Workbench' and copy the cookie value of key 'SSESSc2214f6938283aa908e28c4bfa176f5b'\n",
"\n",
"# Now start a browser instance and set cookies required to access 'My Workbench'. If you get an \"Access denied\" error, the cookie value was incorrect.\n",
"browser = webdriver.Chrome(driver_path)\n",
Expand Down
Loading

0 comments on commit 1950d6b

Please sign in to comment.