你可以在返回值后继续遍历列表吗？

Question

I am using selenium to scrape information from yahoo finance ( i know requests and bs4 is better but I wanted to do it this way.) I created a looping function to retrieve the stock ticker symbols from a list, but after it returns the first symbol it just resets and returns the first symbol again on the next loop iteration. I know that return is supposed to break the loop but I don't know any other way to return the value I'm looping for. I was wondering if I could ask you great and powerful oracles for help!!

The function is named miningLoop. Please let me know if you have any questions about this or anything?! I know that i could just put the function inside of the main and loop it there but can I do it from a function outside the main like this?

class miningCompanies():
    def prime(self):
        self.miningscraper()

    def miningscraper(self):
        while True:
            self.driver = webdriver.Chrome('/Users/admin/Downloads/Chromedriver')
            self.driver.get('https://finance.yahoo.com/quote/' + self.val + '?p=' + self.val + '&.tsrc=fin-srch')
            self.driver.implicitly_wait(5)
            time.sleep(5)
            self.scrapeData()
            time.sleep(5)

    def miningLoop(self):


        companies = ["XOM", "PM", "KXPLF", "PLG", "PLM", 'NCPCF', 'SBUM', 'OTMN', 'SLSR', 'NXXGF',
                     'CAHPF', 'FGOVF', 'ISVLF', 'SGRCF', 'KTGDF', 'KOREF', 'AHELF', 'DOLLF', 'DMEHF', 'TLRS', 'SSVFF',
                     'NEVDF', 'NMTLF', 'AAMMF', 'FFMGF', 'GLDLF', 'ELYGF', 'WLBMF', 'LRTNF', 'ANXGF', 'GPL', 'NAK',
                     'MLRKF', 'RVSDF', 'MUX', 'AUY', 'NGD', 'SLVRF', 'GORO', 'GOLD', 'EGO', 'SLVTF', 'ASX:AZS', 'AAGFF',
                     'ORAGF', 'SILV', 'CCJ', 'UEC', 'DGC.TO', 'OR', 'KGC', 'KOOYF', 'SVM', 'KL', 'JAG', 'TUO', 'BNCH', 'DV', 'ABRA', 'SDR', 'GGI', 'AUY', 'HMY', 'NST',
                     'BTG', 'EVN', 'SAR', 'EDV', 'EQX', 'NG', 'HL', 'PVG', 'SAND', 'CDE', 'MDKA', 'SSRM', 'SILV',
                     'USAS', 'AXU', 'GBR', 'AR', 'HGM', 'GOR', 'WGX', 'LUG', 'HOC', 'POG', 'TXG', 'MAG', 'FSM', 'CEY',
                     'RRL', 'SLR', 'AG', 'AAU', 'TGLDF', 'KLR']

        list = len(companies)
        for x in range(list):
            val = companies[x]
            x += 1


    def scrapeData(self):
        self.driver.implicitly_wait(10)
        time.sleep(2)
        self.PreviousClose = self.driver.find_element_by_xpath('//*[@id="quote-summary"]/div[1]/table/tbody/tr[1]/td[2]/span')
        self.EPS = self.driver.find_element_by_xpath('//*[@id="quote-summary"]/div[2]/table/tbody/tr[4]/td[2]/span')
        self.Market_Cap = self.driver.find_element_by_xpath('//*[@id="quote-summary"]/div[2]/table/tbody/tr[1]/td[2]/span')
        self.PE_Ratio = self.driver.find_element_by_xpath('//*[@id="quote-summary"]/div[2]/table/tbody/tr[3]/td[2]/span')
        self.Dividend = self.driver.find_element_by_xpath('//*[@id="quote-summary"]/div[2]/table/tbody/tr[6]/td[2]')
        self.apiDrive1()
        self.driver.implicitly_wait(10)
        time.sleep(3)
        statistics = self.driver.find_element_by_xpath('//*[@id="quote-nav"]/ul/li[5]/a/span')
        statistics.click()
        self.driver.implicitly_wait(10)
        time.sleep(3)
        self.shareShort = self.driver.find_element_by_xpath('//*[@id="Col1-0-KeyStatistics-Proxy"]/section/div[3]/div[2]/div/div[2]/div/div/table/tbody/tr[7]/td[2]')
        self.institutions = self.driver.find_element_by_xpath('//*[@id="Col1-0-KeyStatistics-Proxy"]/section/div[3]/div[2]/div/div[2]/div/div/table/tbody/tr[6]/td[2]')
        self.revenue = self.driver.find_element_by_xpath('//*[@id="Col1-0-KeyStatistics-Proxy"]/section/div[3]/div[3]/div/div[4]/div/div/table/tbody/tr[1]/td[2]')
        self.high = self.driver.find_element_by_xpath('//*[@id="Col1-0-KeyStatistics-Proxy"]/section/div[3]/div[2]/div/div[1]/div/div/table/tbody/tr[4]/td[2]')
        self.low = self.driver.find_element_by_xpath('//*[@id="Col1-0-KeyStatistics-Proxy"]/section/div[3]/div[2]/div/div[1]/div/div/table/tbody/tr[5]/td[2]')
        self.insiders = self.driver.find_element_by_xpath('//*[@id="Col1-0-KeyStatistics-Proxy"]/section/div[3]/div[2]/div/div[2]/div/div/table/tbody/tr[5]/td[2]')
        self.apiDrive2()
        #self.financial = self.driver.find_element_by_xpath('//*[@id="quote-nav"]/ul/li[8]/a/span')
        #financial.click()
        self.driver.implicitly_wait(3)
        time.sleep(2)
        self.driver.close()

    def apiDrive1(self):
        scope = ["https://spreadsheets.google.com/feeds", 'https://www.googleapis.com/auth/spreadsheets',
                 "https://www.googleapis.com/auth/drive.file", "https://www.googleapis.com/auth/drive"]

        creds = ServiceAccountCredentials.from_json_keyfile_name("creds.json", scope)
        client = gspread.authorize(creds)
        sheet = client.open("Company Break Down").sheet1  # Open the spreadhseet
        data = sheet.get_all_records()
        #first page loop
        x = 106
        i = 1
        while i < x:
            if i == 24 or 43 or 63 or 84 or 102:
                i += 1
            # you have to put a cool down time between requests or Google API will reject you
            self.MC = sheet.update_cell(i, 2, self.Market_Cap.text)
            time.sleep(0.2)
            self.PC = sheet.update_cell(i, 4, self.PreviousClose.text)
            time.sleep(0.2)
            self.PER = sheet.update_cell(i, 19, self.PE_Ratio.text)
            time.sleep(0.2)
            self.EPSC = sheet.update_cell(i, 21, self.EPS.text)
            time.sleep(0.2)
            self.Div = sheet.update_cell(i, 23, self.Dividend.text)
            time.sleep(0.2)
            i += 1
            break


    def apiDrive2(self):
        self.driver.implicitly_wait(10)
        time.sleep(5)
        scope = ["https://spreadsheets.google.com/feeds", 'https://www.googleapis.com/auth/spreadsheets',
                 "https://www.googleapis.com/auth/drive.file", "https://www.googleapis.com/auth/drive"]

        creds = ServiceAccountCredentials.from_json_keyfile_name("creds.json", scope)
        client = gspread.authorize(creds)
        sheet = client.open("Company Break Down").sheet1  # Open the spreadhseet
        data = sheet.get_all_records()
        x = 106
        i = 1
        while i < x:
            if i == 24 or 43 or 63 or 84 or 102:
                i += 1
            # you have to put a cool down time between requests or Google API will reject you
            self.institution = sheet.update_cell(i, 7, self.institutions.text)
            time.sleep(0.2)
            self.short = sheet.update_cell(i, 28, self.shareShort.text)
            time.sleep(0.2)
            self.rev = sheet.update_cell(i, 21, self.revenue.text)
            time.sleep(0.2)
            self.high52 = sheet.update_cell(i, 34, self.high.text)
            time.sleep(0.2)
            self.insider = sheet.update_cell(i, 8, self.insiders.text)
            time.sleep(0.2)
            self.low52 = sheet.update_cell(i, 33, self.low.text)
            i += 1
            break





beserk = miningCompanies()
beserk.prime()

Answer 1

The line if i == 24 or 43 or 63 or 84 or 102: is actually being executed like this:

if (i == 24) or (43) or (63) or (84) or (102):
    ...

So it tries to evaluate i == 24 , and if that fails, it checks if 43 is True , which is always the case.

Instead you need to rewrite i == x for each number, or use the in operator:

if i in {24, 43, 63, 84, 102}:
    ...

If this doesn't fix your issue, you'll need to explain what part of your code doesn't work, and what outcome you are expecting

Answer 2

Going back to your original question. If you are iterating through a list and return from the function that contains the iterator, then you lose the iterator. You might want to look at generators, and use yield instead of return .