Salastil/selenium-twitter-scraper
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

twitter scraper script

Browse Source
This commit is contained in:
Jarrian
2023-09-09 12:23:18 +08:00
parent e4e46c9802
commit 783294a1ed
9 changed files with 492 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
main.ipynb
View File

@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 46,
"metadata": {},
"outputs": [],
"source": [
@@ -34,7 +34,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 47,
"metadata": {},
"outputs": [],
"source": [
@@ -57,7 +57,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 48,
"metadata": {},
"outputs": [],
"source": [
@@ -79,7 +79,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 49,
"metadata": {},
"outputs": [],
"source": [
@@ -193,7 +193,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 50,
"metadata": {},
"outputs": [],
"source": [
@@ -286,16 +286,16 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": 51,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Progress: [[=======---------------------------------]] 18.00% 9 of 50\n",
"Scraping Incomplete\n",
"Tweets: 9 out of 50\n"
"Progress: [[========================================]] 100.00% 50 of 50\n",
"Scraping Complete\n",
"Tweets: 50 out of 50\n"
]
}
],
@@ -371,7 +371,7 @@
},
{
"cell_type": "code",
"execution_count": 16,
"execution_count": 52,
"metadata": {},
"outputs": [],
"source": [
@@ -397,7 +397,7 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": 53,
"metadata": {},
"outputs": [],
"source": [
@@ -413,7 +413,7 @@
},
{
"cell_type": "code",
"execution_count": 18,
"execution_count": 54,
"metadata": {},
"outputs": [],
"source": [
@@ -430,7 +430,7 @@
"\n",
"df = pd.DataFrame(data)\n",
"\n",
"current_time = datetime.now().strftime(\"%Y-%m-%d-%H-%M\")\n",
"current_time = datetime.now().strftime(\"%Y-%m-%d_%H-%M-%S\")\n",
"\n",
"file_path = f'{folder_path}{current_time}_tweets_1-{len(scraper.data)}.csv'\n",
"df.to_csv(file_path, index=False)\n"