我的代碼：
from bs4 import BeautifulSoup as soup
from numpy.lib.function_base import extract
import requests
import pandas as pd
Scraper2Excel = "C:\\Users\\Ashley\\FromPython3.xlsx"
writer = pd.ExcelWriter(Scraper2Excel, engine='xlsxwriter')
READ = "C:\\Users\\Ashley\\URLs List.xlsx"
Tickers1 = pd.read_excel(READ, sheet_name='Tickers', header=None)
Tickers = Tickers1.values.ravel()
print(Tickers)
UniformResourceLocators = pd.read_excel(READ, sheet_name= 'URLs', header=None, skiprows=1)
UniformResourceLocatorsTitles = pd.read_excel(READ, sheet_name='URLs', header=None, nrows=1).values[0]
UniformResourceLocators.columns = UniformResourceLocatorsTitles
URLs = UniformResourceLocators['Company News URL']
tick = UniformResourceLocators['Tickers']
startrow =0
for i in Tickers:
s = Tickers1.loc[(Tickers1[0]==i)]
print(s)
s.to_excel(writer, sheet_name='Sheet1', startrow= startrow, startcol= 0, header=False, index=False)
startrow = 1
url = URLs.loc[(tick==i)]
print(url)
for i in url:
html_text = requests.get(i).text
chickennoodle = soup(html_text, 'html.parser')
for link in chickennoodle.find_all('a'):
my_links = (link.get('href'))
print(my_links)
我被困在這里。my_links以字串格式列印一堆 URL，我想將它們輸出到 excel 檔案中。我一直無法找到將其轉換為 DataFrame 的方法，因此 pandas 會讓我使用to_excel. 我是新手，非常感謝您的幫助。
#df = my_links??
df.to_excel(writer, sheet_name='Sheet2', startrow= startrow, startcol=0, header=False, index=False)
startrow = 1
writer.save()
uj5u.com熱心網友回復：
我要做的是在你的 for 回圈之前啟動一個空串列，然后在你的回圈中將“my_links”附加到該串列中。
然后在代碼結束時，您可以將該串列轉換為 df 的一列，然后再匯出到 excel。就像是
mylinksList=[]
df=pd.DataFrame()
for i in url:
html_text = requests.get(i).text
chickennoodle = soup(html_text, 'html.parser')
for link in chickennoodle.find_all('a'):
my_links = (link.get('href'))
mylinksList.append(my_links)
df['links']=pd.Series(mylinksList)
轉載請註明出處，本文鏈接：https://www.uj5u.com/gongcheng/468107.html
上一篇：查找字串結尾的最快方法