From a86165158086e3c5ed0f25890b8b7838d7b371b9 Mon Sep 17 00:00:00 2001
From: Jaivardhan Shukla <93859359+jaivsh@users.noreply.github.com>
Date: Thu, 10 Aug 2023 22:49:44 +0530
Subject: [PATCH 1/3] Create bbc.py
---
BBC Scraper/bbc.py | 111 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 111 insertions(+)
create mode 100644 BBC Scraper/bbc.py
diff --git a/BBC Scraper/bbc.py b/BBC Scraper/bbc.py
new file mode 100644
index 0000000000..bca3b7185f
--- /dev/null
+++ b/BBC Scraper/bbc.py
@@ -0,0 +1,111 @@
+from bs4 import BeautifulSoup
+import requests
+
+
+class NewsCNN:
+ """
+ Create an instance of `NewsCNN` class.\n
+ ```python
+ news = NewsCNN()
+ ```
+ | Methods | Details |
+ | ---------------------------- | -------------------------------------------------------------------------- |
+ | `.news_by_location(country="india)` | Returns the list of articles by a specific country. |
+ | `.news_by_category(type)` | Returns the list of articles by a specific category. |
+ """
+
+ def __init__(self):
+ self.headers = {
+ "User-Agent": "Mozilla/5.0 (Windows NT 6.3; Win 64 ; x64) Apple WeKit /537.36(KHTML , like Gecko) Chrome/80.0.3987.162 Safari/537.36"
+ }
+
+ def news_by_location(self, country: str):
+ """
+ Returns the relevant news articles corresponding to that particular geo-continent or country\n
+ Class - `NewsCNN`
+ Parameters: \n
+ - country: Name of the country\n
+ ```python
+ news = newsCNN()
+ news.news_by_location()
+ ```
+ """
+
+ try:
+ sol = []
+ obj_keys = ["news", "link"]
+ location = country.lower()
+ URL = f"https://edition.cnn.com/world/{location}"
+ page = requests.get(URL)
+ parse = BeautifulSoup(page.content, "html.parser")
+ heads = parse.find_all("span", attrs={"data-editable": "headline"})
+ links1 = parse.find_all(
+ "a",
+ attrs={
+ "class": "container__link container_lead-plus-headlines-with-images__link"
+ },
+ )
+ links2 = parse.find_all(
+ "a", attrs={"class": "container__link container_vertical-strip__link"}
+ )
+ links3 = parse.find_all(
+ "a",
+ attrs={"class": "container__link container_lead-plus-headlines__link"},
+ )
+
+ base = "https://edition.cnn.com/"
+ allurls = []
+ allheads = []
+
+ for i in heads:
+ tmp = i.text
+ allheads.append(tmp)
+
+ for i in links1 + links2 + links3:
+ t = base + i["href"]
+ allurls.append(t)
+ allurls = list(set(allurls))
+
+ for i in range(len(allurls)):
+ obj_values = [allheads[i], allurls[i]]
+ new_obj = dict(zip(obj_keys, obj_values))
+ sol.append(new_obj)
+
+ return sol
+ except:
+ return None
+
+ def news_by_category(self, type: str):
+ """
+ Returns a list of news articles from a specific category.
+
+ Parameters:
+ - type (str): The category of news articles to retrieve. Allowable types are: "politics", "business", "opinions", "health", "style".
+
+ Returns:
+ A list of dictionaries, each containing news article information including title and link, or an exception if an error occurs.
+
+ Example:
+ ```python
+ news = NewsCNN()
+ politics_articles = news.news_by_category("politics")
+ ```
+ """
+ try:
+ sol = []
+ type = type.lower()
+ url = f"https://edition.cnn.com/{type}"
+ page = requests.get(url, headers=self.headers)
+ parse = BeautifulSoup(page.content, "html.parser")
+ articles = parse.find_all(
+ "a", {"class": "container__link container_lead-plus-headlines__link"}
+ )
+ for article in articles:
+ text = article.find("span", {"data-editable": "headline"})
+ if text:
+ link = "https://edition.cnn.com" + article["href"]
+ data = {"Title": text.text, "Link": link}
+ sol.append(data)
+ return sol
+ except Exception as e:
+ return e
From 5dc68cceb6bc6a2aa964467d61311076b4b5fc0c Mon Sep 17 00:00:00 2001
From: Jaivardhan Shukla <93859359+jaivsh@users.noreply.github.com>
Date: Thu, 10 Aug 2023 22:50:41 +0530
Subject: [PATCH 2/3] Create requirements.txt
---
BBC Scraper/requirements.txt | 3 +++
1 file changed, 3 insertions(+)
create mode 100644 BBC Scraper/requirements.txt
diff --git a/BBC Scraper/requirements.txt b/BBC Scraper/requirements.txt
new file mode 100644
index 0000000000..5d3386da47
--- /dev/null
+++ b/BBC Scraper/requirements.txt
@@ -0,0 +1,3 @@
+beautifulsoup4==4.9.1
+bs4==0.0.1
+requests==2.31.0
From 143b50ded65d31dfbe3458427603d52e8a0b1c82 Mon Sep 17 00:00:00 2001
From: Jaivardhan Shukla <93859359+jaivsh@users.noreply.github.com>
Date: Thu, 10 Aug 2023 22:51:06 +0530
Subject: [PATCH 3/3] Delete BBC Scraper directory
---
BBC Scraper/bbc.py | 111 -----------------------------------
BBC Scraper/requirements.txt | 3 -
2 files changed, 114 deletions(-)
delete mode 100644 BBC Scraper/bbc.py
delete mode 100644 BBC Scraper/requirements.txt
diff --git a/BBC Scraper/bbc.py b/BBC Scraper/bbc.py
deleted file mode 100644
index bca3b7185f..0000000000
--- a/BBC Scraper/bbc.py
+++ /dev/null
@@ -1,111 +0,0 @@
-from bs4 import BeautifulSoup
-import requests
-
-
-class NewsCNN:
- """
- Create an instance of `NewsCNN` class.\n
- ```python
- news = NewsCNN()
- ```
- | Methods | Details |
- | ---------------------------- | -------------------------------------------------------------------------- |
- | `.news_by_location(country="india)` | Returns the list of articles by a specific country. |
- | `.news_by_category(type)` | Returns the list of articles by a specific category. |
- """
-
- def __init__(self):
- self.headers = {
- "User-Agent": "Mozilla/5.0 (Windows NT 6.3; Win 64 ; x64) Apple WeKit /537.36(KHTML , like Gecko) Chrome/80.0.3987.162 Safari/537.36"
- }
-
- def news_by_location(self, country: str):
- """
- Returns the relevant news articles corresponding to that particular geo-continent or country\n
- Class - `NewsCNN`
- Parameters: \n
- - country: Name of the country\n
- ```python
- news = newsCNN()
- news.news_by_location()
- ```
- """
-
- try:
- sol = []
- obj_keys = ["news", "link"]
- location = country.lower()
- URL = f"https://edition.cnn.com/world/{location}"
- page = requests.get(URL)
- parse = BeautifulSoup(page.content, "html.parser")
- heads = parse.find_all("span", attrs={"data-editable": "headline"})
- links1 = parse.find_all(
- "a",
- attrs={
- "class": "container__link container_lead-plus-headlines-with-images__link"
- },
- )
- links2 = parse.find_all(
- "a", attrs={"class": "container__link container_vertical-strip__link"}
- )
- links3 = parse.find_all(
- "a",
- attrs={"class": "container__link container_lead-plus-headlines__link"},
- )
-
- base = "https://edition.cnn.com/"
- allurls = []
- allheads = []
-
- for i in heads:
- tmp = i.text
- allheads.append(tmp)
-
- for i in links1 + links2 + links3:
- t = base + i["href"]
- allurls.append(t)
- allurls = list(set(allurls))
-
- for i in range(len(allurls)):
- obj_values = [allheads[i], allurls[i]]
- new_obj = dict(zip(obj_keys, obj_values))
- sol.append(new_obj)
-
- return sol
- except:
- return None
-
- def news_by_category(self, type: str):
- """
- Returns a list of news articles from a specific category.
-
- Parameters:
- - type (str): The category of news articles to retrieve. Allowable types are: "politics", "business", "opinions", "health", "style".
-
- Returns:
- A list of dictionaries, each containing news article information including title and link, or an exception if an error occurs.
-
- Example:
- ```python
- news = NewsCNN()
- politics_articles = news.news_by_category("politics")
- ```
- """
- try:
- sol = []
- type = type.lower()
- url = f"https://edition.cnn.com/{type}"
- page = requests.get(url, headers=self.headers)
- parse = BeautifulSoup(page.content, "html.parser")
- articles = parse.find_all(
- "a", {"class": "container__link container_lead-plus-headlines__link"}
- )
- for article in articles:
- text = article.find("span", {"data-editable": "headline"})
- if text:
- link = "https://edition.cnn.com" + article["href"]
- data = {"Title": text.text, "Link": link}
- sol.append(data)
- return sol
- except Exception as e:
- return e
diff --git a/BBC Scraper/requirements.txt b/BBC Scraper/requirements.txt
deleted file mode 100644
index 5d3386da47..0000000000
--- a/BBC Scraper/requirements.txt
+++ /dev/null
@@ -1,3 +0,0 @@
-beautifulsoup4==4.9.1
-bs4==0.0.1
-requests==2.31.0