Add files via upload (#961)

<!-- If this is your first pull request: sign the CLA with this GitHub
app: https://cla-assistant.io/renovatebot/renovate -->
<!-- Make sure the `Allow edits and access to secrets by maintainers`
checkbox is checked on this pull request. -->
<!-- Please read
https://github.com/renovatebot/renovate/blob/main/.github/contributing.md
before you create your pull request.-->

## Changes

<!-- Describe what behavior is changed by this PR. -->

## Context

<!-- Describe why you're making these changes if it's not already
explained in a corresponding issue. -->
<!-- If you're closing an existing issue with this pull request, use the
keyword Closes #issue_number. -->
<!-- If you're referencing an issue with this pull request, put it in a
Markdown list like this: - #issue_number. -->

## Documentation (please check one with an [x])

- [ ] I have updated the documentation, or
- [ ] No documentation update is required

## How I've tested my work (please select one)

I have verified these changes via:

- [ ] Code inspection only, or
- [ ] Newly added/modified unit tests, or
- [ ] No unit tests but ran on a real repository, or
- [ ] Both unit tests + ran on a real repository

<!-- Do you have any suggestions about this PR template? Edit it here:
https://github.com/renovatebot/renovate/edit/main/.github/pull_request_template.md
-->

<!-- Please do not force push to your PR's branch after you have created
your PR, as doing so forces us to review the whole PR again. This makes
it harder for us to review your work because we don't know what has
changed. -->
<!-- PRs will always be squashed by us when we merge your work. Commit
as many times as you need in this branch. -->

Author: FabianaCampanari

project_Hacker_stanbul University Newspapers Webscraping/stanbul University Newspapers Webscraping.py

@@ -0,0 +1,97 @@
+#Code to download newspapers from Istanbul University
+import webbrowser
+
+import requests,os,lxml
+from bs4 import BeautifulSoup
+
+
+
+
+class DownloadIstanbul:
+
+    def __init__(self):
+
+        main_webpage = "http://nek.istanbul.edu.tr:4444/ekos/GAZETE/index.php#gazete"
+        soup = BeautifulSoup(requests.get(url=main_webpage).text,"lxml")
+        self.newspaper_links = [f"http://nek.istanbul.edu.tr:4444/ekos/GAZETE/{link['href']}" for link in soup.find_all("a",href=True,class_="popular-category h-40")]
+        self.newspaper_names = [span.text for span in soup.find_all("span",class_="caption mb-2 d-block")]
+
+
+    #This method will download all the newspapers
+    def download_all(self):
+
+        for i in range(len(self.newspaper_links)):
+
+            newspaper_link = self.newspaper_links[i]
+            newspaper_name = self.newspaper_names[i]
+
+            os.makedirs(newspaper_name)
+
+            newspaper_soup = BeautifulSoup(requests.get(url=newspaper_link).text,"lxml")
+            newspapers = [anchor_tag["href"].replace(" ","%20") for anchor_tag in newspaper_soup.find_all("a") if "pdf" in anchor_tag["href"]]
+
+            for newspaper in newspapers:
+
+                response = requests.get(url=newspaper)
+                filename = newspaper.replace("%20"," ").split("/")[-1]
+
+                if response.status_code == 200:
+                    with open(f"{newspaper_name}/{filename}","wb") as f:
+                        f.write(response.content)
+                    print(f"{filename} was downloaded")
+                    with open("download_results.txt","a") as f:
+                        f.write(f"{filename} was downloaded\n")
+                else:
+                    print(f"{newspaper_name} had response status code {response.status_code}")
+                    with open("download_results.txt","a") as f:
+                        f.write(f"{newspaper_name} had response status code {response.status_code}")
+
+    #You can use to find this to get the names of the newspapers
+    #it will really useful for the download_newspaper methoad
+    #You can just the copy paste the newspaper you want to download for the newspaper_name input
+    def show_newspaper_list(self):
+        print(self.newspaper_names)
+
+    #This method downloads all of a newspaper
+    def download_newspaper(self,newspaper_name:str):
+
+        if newspaper_name in self.newspaper_names:
+
+            index = self.newspaper_names.index(newspaper_name)
+            newspaper_link = self.newspaper_links[index]
+
+
+            os.makedirs(newspaper_name)
+
+            newspaper_soup = BeautifulSoup(requests.get(url=newspaper_link).text, "lxml")
+            newspapers = [anchor_tag["href"].replace(" ", "%20") for anchor_tag in newspaper_soup.find_all("a") if "pdf" in anchor_tag["href"]]
+
+            for newspaper in newspapers:
+
+                response = requests.get(url=newspaper)
+                filename = newspaper.replace("%20", " ").split("/")[-1]
+
+                if response.status_code == 200:
+                    with open(f"{newspaper_name}/{filename}", "wb") as f:
+                        f.write(response.content)
+                    print(f"{filename} was downloaded")
+                    with open("download_results.txt", "a") as f:
+                        f.write(f"{filename} was downloaded\n")
+                else:
+                    print(f"{newspaper_name} had response status code {response.status_code}")
+                    with open("download_results.txt", "a") as f:
+                        f.write(f"{newspaper_name} had response status code {response.status_code}")
+        else:
+            print(f"Newspaper not found")
+
+
+
+
+if __name__ == "__main__":
+
+    di = DownloadIstanbul()
+    di.show_newspaper_list()
+    #di.download_newspaper("")
+
+
+