|
| 1 | +import requests |
| 2 | +from bs4 import BeautifulSoup |
| 3 | +import json |
| 4 | + |
| 5 | + |
| 6 | +class TechCrunch: |
| 7 | + """ |
| 8 | + Class - `TechCrunch` |
| 9 | + Example: |
| 10 | + ``` |
| 11 | + articles = TechCrunch() |
| 12 | + ```\n |
| 13 | + Methods :\n |
| 14 | + 1. ``.getArticles() | Response - Articles with title, descriptions, images, date and link. |
| 15 | + """ |
| 16 | + |
| 17 | + def get_articles(self, category): |
| 18 | + |
| 19 | + """ |
| 20 | + Class - `TechCrunch` |
| 21 | + Example: |
| 22 | + ``` |
| 23 | + articles = TechCrunch() |
| 24 | + articles.getArticles("artificial-intelligence") |
| 25 | + ``` |
| 26 | + Returns: |
| 27 | + { |
| 28 | + "title": Tile of the article |
| 29 | + "description": Description of the article |
| 30 | + "image": Image of the article |
| 31 | + "author": Author of the Article |
| 32 | + "date": Date the article was posted |
| 33 | + "link": Link to the article |
| 34 | + } |
| 35 | + """ |
| 36 | + url = ( |
| 37 | + "https://techcrunch.com/category/" + category.replace(" ", "-").lower() |
| 38 | + ) |
| 39 | + try: |
| 40 | + res = requests.get(url) |
| 41 | + soup = BeautifulSoup(res.text, "html.parser") |
| 42 | + |
| 43 | + articles_data = {"articles": []} |
| 44 | + |
| 45 | + articles = soup.find_all( |
| 46 | + "div", class_="post-block post-block--image post-block--unread" |
| 47 | + ) |
| 48 | + for n in articles: |
| 49 | + name = ( |
| 50 | + n.select_one(".post-block__title__link") |
| 51 | + .getText() |
| 52 | + .strip() |
| 53 | + .encode("ascii", "ignore") |
| 54 | + .decode() |
| 55 | + ) |
| 56 | + desc = ( |
| 57 | + n.select_one(".post-block__content") |
| 58 | + .getText() |
| 59 | + .strip() |
| 60 | + .encode("ascii", "ignore") |
| 61 | + .decode() |
| 62 | + ) |
| 63 | + img = n.find_all("img", src=True) |
| 64 | + image = img[0]["src"] |
| 65 | + author = ( |
| 66 | + n.select_one(".river-byline__authors") |
| 67 | + .getText() |
| 68 | + .strip() |
| 69 | + .encode("ascii", "ignore") |
| 70 | + .decode() |
| 71 | + ) |
| 72 | + time = n.find_all("div", class_="river-byline") |
| 73 | + date = ( |
| 74 | + time[0] |
| 75 | + .select_one(".river-byline__time") |
| 76 | + .getText() |
| 77 | + .strip() |
| 78 | + .encode("ascii", "ignore") |
| 79 | + .decode() |
| 80 | + ) |
| 81 | + links = n.find_all("a", class_="post-block__title__link", href=True) |
| 82 | + link = links[0]["href"] |
| 83 | + articles_data["articles"].append( |
| 84 | + { |
| 85 | + "title": name, |
| 86 | + "description": desc, |
| 87 | + "image": image, |
| 88 | + "author": author, |
| 89 | + "date": date, |
| 90 | + "link": link, |
| 91 | + } |
| 92 | + ) |
| 93 | + res_json = json.dumps(articles_data) |
| 94 | + return res_json |
| 95 | + except ValueError: |
| 96 | + error_message = { |
| 97 | + "message": "Can't fetch any articles from the topic provided." |
| 98 | + } |
| 99 | + ejson = json.dumps(error_message) |
| 100 | + return ejson |
| 101 | + |
| 102 | + def search(self, topic): |
| 103 | + |
| 104 | + """ |
| 105 | + Class - `TechCrunch` |
| 106 | + Example: |
| 107 | + ``` |
| 108 | + articles = TechCrunch() |
| 109 | + articles.search("github") |
| 110 | + ``` |
| 111 | + Returns: |
| 112 | + { |
| 113 | + "title": Tile of the article |
| 114 | + "description": Description of the article |
| 115 | + "image": Image of the article |
| 116 | + "author": Author of the Article |
| 117 | + "date": Date the article was posted |
| 118 | + "link": Link to the article |
| 119 | + } |
| 120 | + """ |
| 121 | + url = "https://search.techcrunch.com/search?p=" + topic + "&fr=techcrunch" |
| 122 | + try: |
| 123 | + res = requests.get(url) |
| 124 | + soup = BeautifulSoup(res.text, "html.parser") |
| 125 | + |
| 126 | + articles_data = {"articles": []} |
| 127 | + |
| 128 | + articles = soup.find_all("li", class_="ov-a mt-0 pt-26 pb-26 bt-dbdbdb") |
| 129 | + for i in articles: |
| 130 | + name = i.find("a", class_="fz-20 lh-22 fw-b").getText() |
| 131 | + desc = i.find("p", class_="fz-14 lh-20 c-777").getText() |
| 132 | + img = i.find("img", class_="s-img mr-10 s-img-errchk", src=True) |
| 133 | + image = img["src"] |
| 134 | + author = i.find("span", class_="mr-15").getText() |
| 135 | + date = i.find("span", class_="pl-15 bl-1-666").getText() |
| 136 | + links = i.find("a", class_="fz-20 lh-22 fw-b", href=True) |
| 137 | + link = links["href"] |
| 138 | + articles_data["articles"].append( |
| 139 | + { |
| 140 | + "title": name, |
| 141 | + "description": desc, |
| 142 | + "image": image, |
| 143 | + "author": author, |
| 144 | + "date": date, |
| 145 | + "link": link, |
| 146 | + } |
| 147 | + ) |
| 148 | + return articles_data |
| 149 | + except ValueError: |
| 150 | + error_message = { |
| 151 | + "message": "Can't fetch any articles from the topic provided." |
| 152 | + } |
| 153 | + ejson = json.dumps(error_message) |
| 154 | + return ejson |
0 commit comments