我用這個代碼用 jupiter notebook 測試了我的代碼...rname = soup.find('p', 'con_tx')#rnamelis = rname.findAll('p')rnamefrom urllib.request import urljoin story=[] #review_text = lis[0].find('p').getText() #list_soup =soup.find_all('p', 'con_tx') story=rname.getText() story它運作良好。（結果）“我的前女友……”但是當我試圖抓取多個頁面時from bs4 import BeautifulSoupfrom urllib.request import urlopenfrom urllib.request import urljoinimport pandas as pdimport numpy as npimport requestsbase_url = 'https://movie.naver.com/movie/bi/mi/basic.nhn?code='pages =['177374','164102']url = base_url + pages[0]story = []for n in pages: # Create url url = base_url + n # Parse data using BS print('Downloading page %s...' % url) res = requests.get(url) res.raise_for_status() html = urlopen(url) soup = BeautifulSoup(html, "html.parser") #print(soup.find('p', 'con_tx')) rname = soup.find('p', 'con_tx') story=rname.getText() data = {story} df = pd.DataFrame(data) df.head() df.to_csv('./moviestory.csv', sep=',', encoding='EUC-KR')一條錯誤消息出來了。ValueError：未正確調用 DataFrame 構造函數！如何修復我的代碼？
1 回答
慕萊塢森
TA貢獻1810條經驗 獲得超4個贊
不確定您要做什么，但我注意到的一件事是您每次都在覆蓋您的數據框。也不知道為什么將故事初始化為列表，然后將其作為字典存儲在循環中。
from bs4 import BeautifulSoup
import pandas as pd
import requests
base_url = 'https://movie.naver.com/movie/bi/mi/basic.nhn?code='
pages =['177374','164102']
df = pd.DataFrame()
for n in pages:
# Create url
url = base_url + n
# Parse data using BS
print('Downloading page %s...' % url)
res = requests.get(url)
soup = BeautifulSoup(res.text, "html.parser")
rname = soup.find('p', 'con_tx')
story=rname.getText()
data = [story]
df = df.append(pd.DataFrame(data), sort=True).reset_index(drop=True)
df.to_csv('./moviestory.csv', sep=',', encoding='EUC-KR')
添加回答
舉報
0/150
提交
取消