Initial commit

MajidAli44 · Jul 3, 2021 · da0ea52 · da0ea52
commit da0ea52
Show file tree

Hide file tree

Showing 15 changed files with 250 additions and 0 deletions.
diff --git a/.idea/.gitignore b/.idea/.gitignore
diff --git a/.idea/WEbScraping.iml b/.idea/WEbScraping.iml
diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml
diff --git a/.idea/misc.xml b/.idea/misc.xml
diff --git a/.idea/modules.xml b/.idea/modules.xml
diff --git a/Index.html b/Index.html
@@ -0,0 +1,53 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <!-- Required meta tags -->
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+
+    <!-- Bootstrap CSS -->
+    <link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-+0n0xVW2eSR5OomGNYDnhzAbDsOXxcvSN1TPprVMTNDbiYZCxYbOOl7+AMvyTG2x" crossorigin="anonymous">
+
+    <title>My Course</title>
+  </head>
+    <body>
+        <h1>Hello, Start learning!!</h1>
+        <div class="card" id ="card-python-for-beginners">
+            <div class="card-header">
+                Python
+            </div>
+            <div class="card-body">
+                <h5 class="card-title">Python for beginners</h5>
+                <p class="card-text">If you are new to python this is the course that you should buy!</p>
+                <a href="#" class="btn btn-primary">Start for 20$</a>
+            </div>
+        </div>
+
+        <div class="card" id ="card-python-web-development">
+            <div class="card-header">
+                Python
+            </div>
+            <div class="card-body">
+                <h5 class="card-title">Python Web Development</h5>
+                <p class="card-text">If you feel enough Confident with Python, you are ready to learn how to create your own website</p>
+                <a href="#" class="btn btn-primary">Start for 50$</a>
+            </div>
+        </div>
+
+        <div class="card" id ="card-python-machine-learning">
+            <div class="card-header">
+                Python
+            </div>
+            <div class="card-body">
+                <h5 class="card-title">Python Machine Learning</h5>
+                <p class="card-text">Become a python Machine learning Master</p>
+                <a href="#" class="btn btn-primary">Start for 100$</a>
+            </div>
+        </div>
+
+        <script src="https://cdn.jsdelivr.net/npm/@popperjs/[email protected]/dist/umd/popper.min.js" integrity="sha384-IQsoLXl5PILFhosVNubq5LC7Qb9DXgDA9i+tQ8Zj3iwWAwPtgFTxbJ8NT4GN1R8p" crossorigin="anonymous"></script>
+        <script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/js/bootstrap.min.js" integrity="sha384-Atwg2Pkwv9vp0ygtn1JAojH0nYbwNJLPhwyoVbhoPwBhjQPR5VtM2+xf0Uwh9KtT" crossorigin="anonymous"></script>
+    </body>
+
+
+</html>
diff --git a/Scraping.py b/Scraping.py
@@ -0,0 +1,36 @@
+from bs4 import BeautifulSoup
+
+with open("Index.html", 'r') as html_file:
+    content=html_file.read()
+    # print(content)
+
+    soup=BeautifulSoup(content, 'lxml')
+    # print(soup.prettify())
+
+
+    # tags=soup.find('h5')
+    # tags = soup.find_all('h5')
+    # print(tags)
+
+    # courses_html_tags=soup.find_all('h5')
+    # for courses in courses_html_tags:
+        # print(courses)
+        # print(courses.text)
+
+    course_card=soup.find_all("div", class_="card")
+    for course in course_card:
+        # print(course)
+        # print(course.h5)
+        course_name=course.h5.text
+        # course_price=course.a.text
+        course_price = course.a.text.split()[-1]
+
+        # print(course_name)
+        # print(course_price)
+
+        print(f'{course_name} cost {course_price}')
+
+
+
+
+
diff --git a/ScrapingRealWebsite.py b/ScrapingRealWebsite.py
@@ -0,0 +1,114 @@
+from bs4 import BeautifulSoup
+import requests
+import time
+
+# html_text=requests.get("https://www.timesjobs.com/candidate/job-search.html?searchType=personalizedSearch&from=submit&txtKeywords=python&txtLocation=").text
+
+# print(html_text)
+
+# soup=BeautifulSoup(html_text,"lxml")
+
+# jobs=soup.find('li', class_ ="clearfix job-bx wht-shd-bx")
+# print(jobs)
+
+# jobs=soup.find_all('li', class_ ="clearfix job-bx wht-shd-bx")
+# print(jobs)
+
+
+# For Single
+
+
+# job=soup.find('li', class_ ="clearfix job-bx wht-shd-bx")
+# company_name=job.find("h3", class_= "joblist-comp-name")
+# skills=job.find("span", class_="srp-skills")
+# category=job.find("strong", class_="blkclor").text.replace(' ','')
+# published_date=job.find("span",class_="sim-posted").text
+# print(published_date)
+
+# print(f'''
+# Job Type: {category}
+# Company Name: {company_name.text.replace(' ','')}
+# Required Skills: {skills.text.replace(' ','')}
+# ''')
+
+# print(company_name.text.replace(' ',''))
+# print(skills.text.replace(' ',''))
+
+
+
+# For Multiple
+
+# jobs=soup.find_all('li', class_ ="clearfix job-bx wht-shd-bx")
+# for job in jobs:
+#     company_name = job.find("h3", class_="joblist-comp-name")
+#     skills = job.find("span", class_="srp-skills")
+#     category = job.find("strong", class_="blkclor").text.replace(' ', '')
+#     published_date = job.find("span", class_="sim-posted").text
+#
+#     print(f'''
+#     Job Type: {category}
+#     Company Name: {company_name.text.replace(' ', '')}
+#     Required Skills: {skills.text.replace(' ', '')}
+#     Publihed Date: {published_date}
+#     ''')
+#
+#     print("--------------------------------------------------------------------")
+
+
+
+
+# jobs=soup.find_all('li', class_ ="clearfix job-bx wht-shd-bx")
+# for job in jobs:
+#     published_date = job.find("span", class_="sim-posted").text
+#     if 'few' in published_date:
+#         company_name = job.find("h3", class_="joblist-comp-name")
+#         skills = job.find("span", class_="srp-skills")
+#         category = job.find("strong", class_="blkclor").text.replace(' ', '')
+#
+#
+#         print(f'''
+#             Job Type: {category}
+#             Company Name: {company_name.text.replace(' ', '')}
+#             Required Skills: {skills.text.replace(' ', '')}
+#             Published Date: {published_date}
+#             ''')
+#
+#         print("--------------------------------------------------------------------")
+
+
+# Adding features to the Projects
+print("Put some skills that you are not familiar with!")
+unfamiliar_skill=input("> ")
+print(f"Filtering Out: {unfamiliar_skill}")
+
+def find_jobs():
+    html_text = requests.get("https://www.timesjobs.com/candidate/job-search.html?searchType=personalizedSearch&from=submit&txtKeywords=python&txtLocation=").text
+
+    soup = BeautifulSoup(html_text, "lxml")
+    jobs = soup.find_all('li', class_="clearfix job-bx wht-shd-bx")
+    for index, job in enumerate(jobs):
+        published_date = job.find("span", class_="sim-posted").text
+        if 'few' in published_date:
+            company_name = job.find("h3", class_="joblist-comp-name").text.replace(' ', '')
+            skills = job.find("span", class_="srp-skills").text.replace(' ', '')
+            more_info = job.header.h2.a["href"]
+
+            if unfamiliar_skill not in skills:
+                with open(f'posts/{index}.txt', 'w') as f:
+                    f.write(f"Company Name: {company_name.strip()}\n")
+                    f.write(f"Required Skills: {skills.strip()}\n")
+                    f.write(f"More Info: {more_info}")
+                print(f"File Save {index} Successfully")
+
+
+
+
+if __name__ == '__main__':
+    while True:
+        find_jobs()
+        time_wait=10
+        print(f'Waiting {time_wait} minutes')
+        time.sleep(10 * 60)
+
+
+
diff --git a/ScrapingRevision.py b/ScrapingRevision.py
diff --git a/posts/12.txt b/posts/12.txt
@@ -0,0 +1,3 @@
+Company Name: SATRAInfrastructureManagement
+Required Skills: algorithms,python,debugging
+More Info: https://www.timesjobs.com/job-detail/python-developer-satra-infrastructure-management-hyderabad-secunderabad-5-to-8-yrs-jobid-NN4FiC2z3rhzpSvf__PLUS__uAgZw==&source=srp
diff --git a/posts/2.txt b/posts/2.txt
@@ -0,0 +1,3 @@
+Company Name: GEMINISOFTWARESOLUTIONS
+Required Skills: python,mobile,svn,nosql,pythonscripting,git,sqldatabase
+More Info: https://www.timesjobs.com/job-detail/qa-python-python-sdet-gemini-software-solutions-gurgaon-4-to-7-yrs-jobid-jsOuZLK8chlzpSvf__PLUS__uAgZw==&source=srp
diff --git a/posts/21.txt b/posts/21.txt
@@ -0,0 +1,3 @@
+Company Name: TandAHRSolutions
+Required Skills: Djangoframework,PythonDeveloper,corepython
+More Info: https://www.timesjobs.com/job-detail/python-developer-tanda-hr-solutions-mohali-3-to-5-yrs-jobid-GTT0grHZP1tzpSvf__PLUS__uAgZw==&source=srp
diff --git a/posts/22.txt b/posts/22.txt
@@ -0,0 +1,3 @@
+Company Name: eastindiasecuritiesltd.
+Required Skills: python,hadoop,machinelearning
+More Info: https://www.timesjobs.com/job-detail/python-engineer-east-india-securities-ltd-kolkata-2-to-5-yrs-jobid-KEkE19WqPbFzpSvf__PLUS__uAgZw==&source=srp
diff --git a/posts/23.txt b/posts/23.txt
@@ -0,0 +1,3 @@
+Company Name: YMGlobalTechnologiesPteLtd
+Required Skills: python,apache,machinelearning
+More Info: https://www.timesjobs.com/job-detail/python-developer-ym-global-technologies-pte-ltd-singapore-4-to-7-yrs-jobid-bRMEk1dtdLBzpSvf__PLUS__uAgZw==&source=srp
diff --git a/posts/3.txt b/posts/3.txt
@@ -0,0 +1,3 @@
+Company Name: GeminiSolutions
+Required Skills: python,mobile,svn,nosql,pythonscripting,git,api,sqldatabase
+More Info: https://www.timesjobs.com/job-detail/qa-python-python-sdet-gemini-solutions-gurgaon-4-to-7-yrs-jobid-eGMLzwOk2QlzpSvf__PLUS__uAgZw==&source=srp