From 1cea8f5ff2f44ffe25b391ff5666f690a0ad742b Mon Sep 17 00:00:00 2001
From: Karen Zeng <karen.zeng@outlook.com>
Date: Wed, 26 Apr 2023 19:14:54 -0400
Subject: [PATCH] final project update

---
 fp1.py   | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 fp2.py   | 10 ++++++++++
 fp2_2.py | 32 ++++++++++++++++++++++++++++++++
 fp2_3.py | 32 ++++++++++++++++++++++++++++++++
 fp2_4.py | 36 ++++++++++++++++++++++++++++++++++++
 hw12.py  |  7 +++++++
 6 files changed, 170 insertions(+)
 create mode 100644 fp1.py
 create mode 100644 fp2.py
 create mode 100644 fp2_2.py
 create mode 100644 fp2_3.py
 create mode 100644 fp2_4.py
 create mode 100644 hw12.py

diff --git a/fp1.py b/fp1.py
new file mode 100644
index 0000000..7c34e0c
--- /dev/null
+++ b/fp1.py
@@ -0,0 +1,53 @@
+from google.cloud import pubsub_v1
+from google.oauth2 import service_account
+import os
+
+os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "C:/Users/Karen/AppData/Roaming/gcloud/application_default_credentials.json"
+project_id = "fp-20230425"
+
+'''
+topic_name = "fp-topic-Karen"
+subscription_name = "fp-subscription-Karen"
+subscriber = pubsub_v1.SubscriberClient()
+subscription_path = f"projects/{project_id}/subscriptions/{subscription_name}"
+subscriber.delete_subscription(request={"subscription": subscription_path})
+print("Subscription deleted: {}".format(subscription_path))
+
+# Delete the topic
+publisher = pubsub_v1.PublisherClient()
+topic_path = publisher.topic_path(project_id, topic_name)
+publisher.delete_topic(request={"topic": topic_path})
+print(f"Topic '{topic_name}' deleted.")
+
+subscription_name = "fp-subscription-Karen"
+subscription_path = f"projects/{project_id}/subscriptions/{subscription_name}"
+
+
+'''
+# Create a pubsub topic
+publisher = pubsub_v1.PublisherClient()
+topic_name = "fp-topic-Karen"
+topic_path = publisher.topic_path(project_id, topic_name)
+topic = publisher.create_topic(request={"name": topic_path})
+
+
+# Create a Pub/Sub subscription
+subscriber = pubsub_v1.SubscriberClient()
+subscription_name = "fp-subscription-Karen"
+subscription_path = subscriber.subscription_path(project_id, subscription_name)
+subscription = subscriber.create_subscription(
+    name=subscription_path, topic=topic_path
+)
+
+# Publish a message to the topic
+message = b"Hello!"
+publisher.publish(topic_path, data=message)
+print("Message published.")
+
+
+# Pull the message from the subscription
+response = subscriber.pull(subscription=subscription_path, max_messages=1)
+for received_message in response.received_messages:
+    print("Received message: {}".format(received_message.message.data))
+    # Acknowledge the message to mark it as processed
+    subscriber.acknowledge(subscription_path, [received_message.ack_id])
diff --git a/fp2.py b/fp2.py
new file mode 100644
index 0000000..6975742
--- /dev/null
+++ b/fp2.py
@@ -0,0 +1,10 @@
+import http.client
+
+# The product ID for the Pete-and-Gerry's organic large brown egges is 65902
+conn = http.client.HTTPSConnection("www.sayweee.com")
+payload = ''
+headers = {}
+conn.request("GET", "/en/product/Pete-and-Gerry-s-Organic-Large-Brown-Eggs/65902?category=dairy02", payload, headers)
+res = conn.getresponse()
+data = res.read()
+print(data.decode("utf-8"))
\ No newline at end of file
diff --git a/fp2_2.py b/fp2_2.py
new file mode 100644
index 0000000..0f5dc63
--- /dev/null
+++ b/fp2_2.py
@@ -0,0 +1,32 @@
+import http.client
+import xml.etree.ElementTree as ET
+
+conn = http.client.HTTPSConnection("www.sayweee.com")
+payload = ''
+headers = {}
+conn.request("GET", "/en/product/Pete-and-Gerry-s-Organic-Large-Brown-Eggs/65902?category=dairy02", payload, headers)
+res = conn.getresponse()
+data = res.read()
+
+# Parse the HTML page content using ElementTree
+root = ET.fromstring(data.decode('utf-8'))
+
+if root is not None:
+    # Find the script element with __NEXT_DATA__ data
+    next_data_element = None
+    for script_element in root.iter('script'):
+        if script_element.text is not None and '__NEXT_DATA__' in script_element.text:
+            next_data_element = script_element
+            break
+
+    # Extract the __NEXT_DATA__ data
+    if next_data_element is not None:
+        next_data_text = next_data_element.txt
+        next_data_start_index = next_data_text.index('{')
+        next_data_end_index = next_data_text.rindex('}') + 1
+        next_data_json = next_data_text[next_data_start_index:next_data_end_index]
+        print(next_data_json)
+    else:
+        print('__NEXT_DATA__ element not found')
+else:
+    print('Failed to parse HTML content')
diff --git a/fp2_3.py b/fp2_3.py
new file mode 100644
index 0000000..4bc14d7
--- /dev/null
+++ b/fp2_3.py
@@ -0,0 +1,32 @@
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+import json
+
+# Configure the Selenium driver options
+options = Options()
+options.add_argument('--headless')
+options.add_argument('--disable-gpu')
+driver = webdriver.Chrome(options=options)
+
+# Load the page and extract the __NEXT_DATA__ data
+url = 'https://www.sayweee.com/en/product/Pete-and-Gerry-s-Organic-Large-Brown-Eggs/65902?category=dairy02'
+driver.get(url)
+wait = WebDriverWait(driver, 10)
+next_data_element = wait.until(EC.presence_of_element_located((By.XPATH, '//script[contains(text(), "__NEXT_DATA__")]')))
+next_data_text = next_data_element.text
+next_data_start_index = next_data_text.index('{')
+next_data_end_index = next_data_text.rindex('}') + 1
+next_data_json = next_data_text[next_data_start_index:next_data_end_index]
+next_data = json.loads(next_data_json)
+
+# Extract the price from the __NEXT_DATA__ data
+price = next_data['props']['pageProps']['product']['price']
+
+# Close the Selenium driver
+driver.quit()
+
+# Print the price
+print(price)
diff --git a/fp2_4.py b/fp2_4.py
new file mode 100644
index 0000000..c8334b6
--- /dev/null
+++ b/fp2_4.py
@@ -0,0 +1,36 @@
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+import json
+
+# Configure the Selenium driver options
+options = Options()
+options.add_argument('--headless')
+options.add_argument('--disable-gpu')
+driver = webdriver.Chrome(options=options)
+
+# Load the page and extract the __NEXT_DATA__ data
+url = 'https://www.sayweee.com/en/product/Pete-and-Gerry-s-Organic-Large-Brown-Eggs/65902?category=dairy02'
+driver.get(url)
+next_data_element = None
+for script_element in driver.find_elements_by_xpath('//script'):
+    if '__NEXT_DATA__' in script_element.get_attribute('innerHTML'):
+        next_data_element = script_element
+        break
+
+if next_data_element is not None:
+    next_data_text = next_data_element.get_attribute('innerHTML')
+    next_data_start_index = next_data_text.index('{')
+    next_data_end_index = next_data_text.rindex('}') + 1
+    next_data_json = next_data_text[next_data_start_index:next_data_end_index]
+    next_data = json.loads(next_data_json)
+
+    # Extract the price from the __NEXT_DATA__ data
+    price = next_data['props']['pageProps']['product']['price']
+
+    # Print the price
+    print(price)
+else:
+    print('__NEXT_DATA__ element not found')
+
+# Close the Selenium driver
+driver.quit()
diff --git a/hw12.py b/hw12.py
new file mode 100644
index 0000000..d19ab2e
--- /dev/null
+++ b/hw12.py
@@ -0,0 +1,7 @@
+i = 5
+
+def f(arg=i):
+    print(arg)
+
+i = 6
+f()
\ No newline at end of file