Support advanced search results

.gitignore

@@ -0,0 +1,152 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

googlesearch/__init__.py

@@ -1,37 +1,63 @@
 from bs4 import BeautifulSoup
 from requests import get
 
+usr_agent = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'}
 
-def search(term, num_results=10, lang="en", proxy=None):
-    usr_agent = {
-        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
-                      'Chrome/61.0.3163.100 Safari/537.36'}
-
-    def fetch_results(search_term, number_results, language_code):
-        escaped_search_term = search_term.replace(' ', '+')
-
-        google_url = 'https://www.google.com/search?q={}&num={}&hl={}'.format(escaped_search_term, number_results+1,
-                                                                              language_code)
-        proxies = None
-        if proxy:
-            if proxy[:5]=="https":
-                proxies = {"https":proxy} 
-            else:
-                proxies = {"http":proxy}
-
-        response = get(google_url, headers=usr_agent, proxies=proxies)    
-        response.raise_for_status()
-
-        return response.text
-
-    def parse_results(raw_html):
-        soup = BeautifulSoup(raw_html, 'html.parser')
+def _req(term, results, lang, start, proxies):
+    resp = get(
+        url="https://www.google.com/search",
+        headers=usr_agent,
+        params=dict(
+            q = term,
+            num = results + 2, # Prevents multiple requests
+            hl = lang,
+            start = start,
+        ),
+        proxies=proxies,
+    )
+    resp.raise_for_status()
+    return resp
+
+class SearchResult:
+    def __init__(self, url, title, description):
+        self.url = url
+        self.title = title
+        self.description = description
+
+    def __repr__(self):
+        return f"SearchResult(url={self.url}, title={self.title}, description={self.description})"
+
+def search(term, num_results=10, lang="en", proxy=None, advanced=False):
+    escaped_term = term.replace(' ', '+')
+
+    # Proxy
+    proxies = None
+    if proxy:
+        if proxy[:5]=="https":
+            proxies = {"https": proxy} 
+        else:
+            proxies = {"http": proxy}
+
+    # Fetch
+    start = 0
+    while start < num_results:
+        # Send request
+        resp = _req(escaped_term, num_results-start, lang, start, proxies)
+
+        # Parse
+        soup = BeautifulSoup(resp.text, 'html.parser')
         result_block = soup.find_all('div', attrs={'class': 'g'})
         for result in result_block:
+            # Find link, title, description
             link = result.find('a', href=True)
             title = result.find('h3')
-            if link and title:
-                yield link['href']
+            description_box = result.find('div', {'style': '-webkit-line-clamp:2'})
+            if description_box:
+                description = description_box.find('span')
+                if link and title and description:
+                    start += 1
+                    if advanced:
+                        yield SearchResult(link['href'], title.text, description.text)
+                    else:
+                        yield link['href']
 
-    html = fetch_results(term, num_results, lang)
-    return list(parse_results(html))