|
| 1 | +from bs4 import BeautifulSoup |
| 2 | +import requests |
| 3 | + |
| 4 | + |
| 5 | +class NewsCNN: |
| 6 | + """ |
| 7 | + Create an instance of `NewsCNN` class.\n |
| 8 | + ```python |
| 9 | + news = NewsCNN() |
| 10 | + ``` |
| 11 | + | Methods | Details | |
| 12 | + | ---------------------------- | -------------------------------------------------------------------------- | |
| 13 | + | `.news_by_location(country="india)` | Returns the list of articles by a specific country. | |
| 14 | + | `.news_by_category(type)` | Returns the list of articles by a specific category. | |
| 15 | + """ |
| 16 | + |
| 17 | + def __init__(self): |
| 18 | + self.headers = { |
| 19 | + "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" |
| 20 | + } |
| 21 | + |
| 22 | + def news_by_location(self, country: str): |
| 23 | + """ |
| 24 | + Returns the relevant news articles corresponding to that particular geo-continent or country\n |
| 25 | + Class - `NewsCNN` |
| 26 | + Parameters: \n |
| 27 | + - country: Name of the country\n |
| 28 | + ```python |
| 29 | + news = newsCNN() |
| 30 | + news.news_by_location() |
| 31 | + ``` |
| 32 | + """ |
| 33 | + |
| 34 | + try: |
| 35 | + sol = [] |
| 36 | + obj_keys = ["news", "link"] |
| 37 | + location = country.lower() |
| 38 | + URL = f"https://edition.cnn.com/world/{location}" |
| 39 | + page = requests.get(URL) |
| 40 | + parse = BeautifulSoup(page.content, "html.parser") |
| 41 | + heads = parse.find_all("span", attrs={"data-editable": "headline"}) |
| 42 | + links1 = parse.find_all( |
| 43 | + "a", |
| 44 | + attrs={ |
| 45 | + "class": "container__link container_lead-plus-headlines-with-images__link" |
| 46 | + }, |
| 47 | + ) |
| 48 | + links2 = parse.find_all( |
| 49 | + "a", attrs={"class": "container__link container_vertical-strip__link"} |
| 50 | + ) |
| 51 | + links3 = parse.find_all( |
| 52 | + "a", |
| 53 | + attrs={"class": "container__link container_lead-plus-headlines__link"}, |
| 54 | + ) |
| 55 | + |
| 56 | + base = "https://edition.cnn.com/" |
| 57 | + allurls = [] |
| 58 | + allheads = [] |
| 59 | + |
| 60 | + for i in heads: |
| 61 | + tmp = i.text |
| 62 | + allheads.append(tmp) |
| 63 | + |
| 64 | + for i in links1 + links2 + links3: |
| 65 | + t = base + i["href"] |
| 66 | + allurls.append(t) |
| 67 | + allurls = list(set(allurls)) |
| 68 | + |
| 69 | + for i in range(len(allurls)): |
| 70 | + obj_values = [allheads[i], allurls[i]] |
| 71 | + new_obj = dict(zip(obj_keys, obj_values)) |
| 72 | + sol.append(new_obj) |
| 73 | + |
| 74 | + return sol |
| 75 | + except: |
| 76 | + return None |
| 77 | + |
| 78 | + def news_by_category(self, type: str): |
| 79 | + """ |
| 80 | + Returns a list of news articles from a specific category. |
| 81 | + |
| 82 | + Parameters: |
| 83 | + - type (str): The category of news articles to retrieve. Allowable types are: "politics", "business", "opinions", "health", "style". |
| 84 | + |
| 85 | + Returns: |
| 86 | + A list of dictionaries, each containing news article information including title and link, or an exception if an error occurs. |
| 87 | + |
| 88 | + Example: |
| 89 | + ```python |
| 90 | + news = NewsCNN() |
| 91 | + politics_articles = news.news_by_category("politics") |
| 92 | + ``` |
| 93 | + """ |
| 94 | + try: |
| 95 | + sol = [] |
| 96 | + type = type.lower() |
| 97 | + url = f"https://edition.cnn.com/{type}" |
| 98 | + page = requests.get(url, headers=self.headers) |
| 99 | + parse = BeautifulSoup(page.content, "html.parser") |
| 100 | + articles = parse.find_all( |
| 101 | + "a", {"class": "container__link container_lead-plus-headlines__link"} |
| 102 | + ) |
| 103 | + for article in articles: |
| 104 | + text = article.find("span", {"data-editable": "headline"}) |
| 105 | + if text: |
| 106 | + link = "https://edition.cnn.com" + article["href"] |
| 107 | + data = {"Title": text.text, "Link": link} |
| 108 | + sol.append(data) |
| 109 | + return sol |
| 110 | + except Exception as e: |
| 111 | + return e |
0 commit comments