From 33dc3403d3fb5273e8d13f2890601e6764a174f6 Mon Sep 17 00:00:00 2001 From: Jarrian Date: Sat, 23 Sep 2023 10:06:39 +0800 Subject: [PATCH] feat: 0 count for no reply, like, retweet, or analytics --- main.ipynb | 12 ++++++++++++ scraper/tweet.py | 12 ++++++++++++ 2 files changed, 24 insertions(+) diff --git a/main.ipynb b/main.ipynb index 5f45a51..9a60194 100644 --- a/main.ipynb +++ b/main.ipynb @@ -194,6 +194,9 @@ " self.reply_cnt = card.find_element(\n", " \"xpath\", './/div[@data-testid=\"reply\"]//span'\n", " ).text\n", + " \n", + " if self.reply_cnt == \"\":\n", + " self.reply_cnt = \"0\"\n", " except NoSuchElementException:\n", " self.reply_cnt = \"0\"\n", "\n", @@ -201,6 +204,9 @@ " self.retweet_cnt = card.find_element(\n", " \"xpath\", './/div[@data-testid=\"retweet\"]//span'\n", " ).text\n", + " \n", + " if self.retweet_cnt == \"\":\n", + " self.retweet_cnt = \"0\"\n", " except NoSuchElementException:\n", " self.retweet_cnt = \"0\"\n", "\n", @@ -208,6 +214,9 @@ " self.like_cnt = card.find_element(\n", " \"xpath\", './/div[@data-testid=\"like\"]//span'\n", " ).text\n", + " \n", + " if self.like_cnt == \"\":\n", + " self.like_cnt = \"0\"\n", " except NoSuchElementException:\n", " self.like_cnt = \"0\"\n", "\n", @@ -215,6 +224,9 @@ " self.analytics_cnt = card.find_element(\n", " \"xpath\", './/a[contains(@href, \"/analytics\")]//span'\n", " ).text\n", + " \n", + " if self.analytics_cnt == \"\":\n", + " self.analytics_cnt = \"0\"\n", " except NoSuchElementException:\n", " self.analytics_cnt = \"0\"\n", "\n", diff --git a/scraper/tweet.py b/scraper/tweet.py index 6d30b87..a1e8e08 100644 --- a/scraper/tweet.py +++ b/scraper/tweet.py @@ -53,6 +53,9 @@ class Tweet: self.reply_cnt = card.find_element( "xpath", './/div[@data-testid="reply"]//span' ).text + + if self.reply_cnt == "": + self.reply_cnt = "0" except NoSuchElementException: self.reply_cnt = "0" @@ -60,6 +63,9 @@ class Tweet: self.retweet_cnt = card.find_element( "xpath", './/div[@data-testid="retweet"]//span' ).text + + if self.retweet_cnt == "": + self.retweet_cnt = "0" except NoSuchElementException: self.retweet_cnt = "0" @@ -67,6 +73,9 @@ class Tweet: self.like_cnt = card.find_element( "xpath", './/div[@data-testid="like"]//span' ).text + + if self.like_cnt == "": + self.like_cnt = "0" except NoSuchElementException: self.like_cnt = "0" @@ -74,6 +83,9 @@ class Tweet: self.analytics_cnt = card.find_element( "xpath", './/a[contains(@href, "/analytics")]//span' ).text + + if self.analytics_cnt == "": + self.analytics_cnt = "0" except NoSuchElementException: self.analytics_cnt = "0"