Google Analytic Webcrawler for every country code












0












$begingroup$


At the moment I'd like recommendation where I can change and what I can use to improve on simplicity and modularity. If I'm practicing good naming conventions as to provide clean readable code. Any critique is much appreciated.



import time
import re
import requests
from bs4 import BeautifulSoup, SoupStrainer
import pandas as pd
from time import sleep

SESSION = requests.Session()


""" This is the Google Analytics Selector Section """


class myGoogleSession:

def fetch_google_xml(self, URL, country_code):
format_url = f"{URL}{country_code}"
response = SESSION.get(format_url)
soup = BeautifulSoup(response.text, 'xml',
parse_only=SoupStrainer('channel'))
return soup


google_session = myGoogleSession()


def google_trends_retriever(URL, country_code):
xml_soup = google_session.fetch_google_xml(URL, country_code)
return[(title.text, re.sub("[+,]", "", traffic.text))
for title, traffic in zip(xml_soup.find_all('title')[1:],
xml_soup.find_all('ht:approx_traffic'))]


def create_pdTrend(data):
check_panda = pd.DataFrame(
google_trends_retriever(GoogleURL, data),
columns=['Title', 'Score']
)
if len(check_panda) == 0:
print('No available data')
else:
return check_panda

""" This is the Country Code Selector Section """


country_code_list =


class myCountryCodeSession:
def fetch_countrycode_html(self, URL):
response = SESSION.get(URL)
soup = BeautifulSoup(response.text, 'html.parser',
parse_only=SoupStrainer('table'))
return soup


countryCode_session = myCountryCodeSession()


def parse_row(url):
rows = countryCode_session.fetch_countrycode_html(url)
_rows = rows.findChildren(['td', 'tr'])
for row in _rows:
cells = row.findChildren('td')[2:3]
for cell in cells:
value = cell.string
country_code_list.append(value[:2])
return None


def create_pdCountryCode(country_code):
return pd.DataFrame({'Country_Code': country_code})


def iterate_List(data):
i = 1
while i < len(data):
selected_CountryCode = get_data_fromList(i)
print(create_pdTrend(selected_CountryCode))
sleep(0.5)
i += 1
else:
print('Has reach the end of i ' + str(i))


def get_data_fromList(num):
key = num-1
for i in country_code_list[key:num]:
return str(i)


if __name__ == '__main__':
""" URL Section """
GoogleURL = "https://trends.google.com/trends/trendingsearches/daily/rss?geo="
CountryCodeURL = "https://countrycode.org/"
"""-------------"""

"""Country Code Section """
parse_row(CountryCodeURL)
"""---------------------"""

"""Google Analytics Section """
iterate_List(country_code_list)
"""-------------------------"""









share|improve this question









$endgroup$

















    0












    $begingroup$


    At the moment I'd like recommendation where I can change and what I can use to improve on simplicity and modularity. If I'm practicing good naming conventions as to provide clean readable code. Any critique is much appreciated.



    import time
    import re
    import requests
    from bs4 import BeautifulSoup, SoupStrainer
    import pandas as pd
    from time import sleep

    SESSION = requests.Session()


    """ This is the Google Analytics Selector Section """


    class myGoogleSession:

    def fetch_google_xml(self, URL, country_code):
    format_url = f"{URL}{country_code}"
    response = SESSION.get(format_url)
    soup = BeautifulSoup(response.text, 'xml',
    parse_only=SoupStrainer('channel'))
    return soup


    google_session = myGoogleSession()


    def google_trends_retriever(URL, country_code):
    xml_soup = google_session.fetch_google_xml(URL, country_code)
    return[(title.text, re.sub("[+,]", "", traffic.text))
    for title, traffic in zip(xml_soup.find_all('title')[1:],
    xml_soup.find_all('ht:approx_traffic'))]


    def create_pdTrend(data):
    check_panda = pd.DataFrame(
    google_trends_retriever(GoogleURL, data),
    columns=['Title', 'Score']
    )
    if len(check_panda) == 0:
    print('No available data')
    else:
    return check_panda

    """ This is the Country Code Selector Section """


    country_code_list =


    class myCountryCodeSession:
    def fetch_countrycode_html(self, URL):
    response = SESSION.get(URL)
    soup = BeautifulSoup(response.text, 'html.parser',
    parse_only=SoupStrainer('table'))
    return soup


    countryCode_session = myCountryCodeSession()


    def parse_row(url):
    rows = countryCode_session.fetch_countrycode_html(url)
    _rows = rows.findChildren(['td', 'tr'])
    for row in _rows:
    cells = row.findChildren('td')[2:3]
    for cell in cells:
    value = cell.string
    country_code_list.append(value[:2])
    return None


    def create_pdCountryCode(country_code):
    return pd.DataFrame({'Country_Code': country_code})


    def iterate_List(data):
    i = 1
    while i < len(data):
    selected_CountryCode = get_data_fromList(i)
    print(create_pdTrend(selected_CountryCode))
    sleep(0.5)
    i += 1
    else:
    print('Has reach the end of i ' + str(i))


    def get_data_fromList(num):
    key = num-1
    for i in country_code_list[key:num]:
    return str(i)


    if __name__ == '__main__':
    """ URL Section """
    GoogleURL = "https://trends.google.com/trends/trendingsearches/daily/rss?geo="
    CountryCodeURL = "https://countrycode.org/"
    """-------------"""

    """Country Code Section """
    parse_row(CountryCodeURL)
    """---------------------"""

    """Google Analytics Section """
    iterate_List(country_code_list)
    """-------------------------"""









    share|improve this question









    $endgroup$















      0












      0








      0





      $begingroup$


      At the moment I'd like recommendation where I can change and what I can use to improve on simplicity and modularity. If I'm practicing good naming conventions as to provide clean readable code. Any critique is much appreciated.



      import time
      import re
      import requests
      from bs4 import BeautifulSoup, SoupStrainer
      import pandas as pd
      from time import sleep

      SESSION = requests.Session()


      """ This is the Google Analytics Selector Section """


      class myGoogleSession:

      def fetch_google_xml(self, URL, country_code):
      format_url = f"{URL}{country_code}"
      response = SESSION.get(format_url)
      soup = BeautifulSoup(response.text, 'xml',
      parse_only=SoupStrainer('channel'))
      return soup


      google_session = myGoogleSession()


      def google_trends_retriever(URL, country_code):
      xml_soup = google_session.fetch_google_xml(URL, country_code)
      return[(title.text, re.sub("[+,]", "", traffic.text))
      for title, traffic in zip(xml_soup.find_all('title')[1:],
      xml_soup.find_all('ht:approx_traffic'))]


      def create_pdTrend(data):
      check_panda = pd.DataFrame(
      google_trends_retriever(GoogleURL, data),
      columns=['Title', 'Score']
      )
      if len(check_panda) == 0:
      print('No available data')
      else:
      return check_panda

      """ This is the Country Code Selector Section """


      country_code_list =


      class myCountryCodeSession:
      def fetch_countrycode_html(self, URL):
      response = SESSION.get(URL)
      soup = BeautifulSoup(response.text, 'html.parser',
      parse_only=SoupStrainer('table'))
      return soup


      countryCode_session = myCountryCodeSession()


      def parse_row(url):
      rows = countryCode_session.fetch_countrycode_html(url)
      _rows = rows.findChildren(['td', 'tr'])
      for row in _rows:
      cells = row.findChildren('td')[2:3]
      for cell in cells:
      value = cell.string
      country_code_list.append(value[:2])
      return None


      def create_pdCountryCode(country_code):
      return pd.DataFrame({'Country_Code': country_code})


      def iterate_List(data):
      i = 1
      while i < len(data):
      selected_CountryCode = get_data_fromList(i)
      print(create_pdTrend(selected_CountryCode))
      sleep(0.5)
      i += 1
      else:
      print('Has reach the end of i ' + str(i))


      def get_data_fromList(num):
      key = num-1
      for i in country_code_list[key:num]:
      return str(i)


      if __name__ == '__main__':
      """ URL Section """
      GoogleURL = "https://trends.google.com/trends/trendingsearches/daily/rss?geo="
      CountryCodeURL = "https://countrycode.org/"
      """-------------"""

      """Country Code Section """
      parse_row(CountryCodeURL)
      """---------------------"""

      """Google Analytics Section """
      iterate_List(country_code_list)
      """-------------------------"""









      share|improve this question









      $endgroup$




      At the moment I'd like recommendation where I can change and what I can use to improve on simplicity and modularity. If I'm practicing good naming conventions as to provide clean readable code. Any critique is much appreciated.



      import time
      import re
      import requests
      from bs4 import BeautifulSoup, SoupStrainer
      import pandas as pd
      from time import sleep

      SESSION = requests.Session()


      """ This is the Google Analytics Selector Section """


      class myGoogleSession:

      def fetch_google_xml(self, URL, country_code):
      format_url = f"{URL}{country_code}"
      response = SESSION.get(format_url)
      soup = BeautifulSoup(response.text, 'xml',
      parse_only=SoupStrainer('channel'))
      return soup


      google_session = myGoogleSession()


      def google_trends_retriever(URL, country_code):
      xml_soup = google_session.fetch_google_xml(URL, country_code)
      return[(title.text, re.sub("[+,]", "", traffic.text))
      for title, traffic in zip(xml_soup.find_all('title')[1:],
      xml_soup.find_all('ht:approx_traffic'))]


      def create_pdTrend(data):
      check_panda = pd.DataFrame(
      google_trends_retriever(GoogleURL, data),
      columns=['Title', 'Score']
      )
      if len(check_panda) == 0:
      print('No available data')
      else:
      return check_panda

      """ This is the Country Code Selector Section """


      country_code_list =


      class myCountryCodeSession:
      def fetch_countrycode_html(self, URL):
      response = SESSION.get(URL)
      soup = BeautifulSoup(response.text, 'html.parser',
      parse_only=SoupStrainer('table'))
      return soup


      countryCode_session = myCountryCodeSession()


      def parse_row(url):
      rows = countryCode_session.fetch_countrycode_html(url)
      _rows = rows.findChildren(['td', 'tr'])
      for row in _rows:
      cells = row.findChildren('td')[2:3]
      for cell in cells:
      value = cell.string
      country_code_list.append(value[:2])
      return None


      def create_pdCountryCode(country_code):
      return pd.DataFrame({'Country_Code': country_code})


      def iterate_List(data):
      i = 1
      while i < len(data):
      selected_CountryCode = get_data_fromList(i)
      print(create_pdTrend(selected_CountryCode))
      sleep(0.5)
      i += 1
      else:
      print('Has reach the end of i ' + str(i))


      def get_data_fromList(num):
      key = num-1
      for i in country_code_list[key:num]:
      return str(i)


      if __name__ == '__main__':
      """ URL Section """
      GoogleURL = "https://trends.google.com/trends/trendingsearches/daily/rss?geo="
      CountryCodeURL = "https://countrycode.org/"
      """-------------"""

      """Country Code Section """
      parse_row(CountryCodeURL)
      """---------------------"""

      """Google Analytics Section """
      iterate_List(country_code_list)
      """-------------------------"""






      python python-3.x pandas beautifulsoup






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked 20 mins ago









      MinialMinial

      495




      495






















          0






          active

          oldest

          votes











          Your Answer





          StackExchange.ifUsing("editor", function () {
          return StackExchange.using("mathjaxEditing", function () {
          StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
          StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["\$", "\$"]]);
          });
          });
          }, "mathjax-editing");

          StackExchange.ifUsing("editor", function () {
          StackExchange.using("externalEditor", function () {
          StackExchange.using("snippets", function () {
          StackExchange.snippets.init();
          });
          });
          }, "code-snippets");

          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "196"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: false,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: null,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });














          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fcodereview.stackexchange.com%2fquestions%2f211654%2fgoogle-analytic-webcrawler-for-every-country-code%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes
















          draft saved

          draft discarded




















































          Thanks for contributing an answer to Code Review Stack Exchange!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          Use MathJax to format equations. MathJax reference.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fcodereview.stackexchange.com%2fquestions%2f211654%2fgoogle-analytic-webcrawler-for-every-country-code%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          404 Error Contact Form 7 ajax form submitting

          How to know if a Active Directory user can login interactively

          TypeError: fit_transform() missing 1 required positional argument: 'X'