鉅亨網基金新聞 - python 爬蟲問題 - iT 邦幫忙::一起幫忙解決難題，拯救 IT 人的一天

鉅亨網基金新聞 - python 爬蟲問題

python 爬蟲網路爬蟲 python爬蟲

Denny Chang 2021-05-17 23:51:44 ‧ 3862 瀏覽

分享至

大家好，小弟是個爬蟲菜鳥，只會美麗的湯，近日爬鉅亨發現都只能爬出相同的文章標題，附件是我的code，謝謝大家~

#鉅亨基金新聞爬蟲 
#https://news.cnyes.com/news/cat/fund
#https://news.cnyes.com/news/id/4646317 #每篇id
#假日無文，先爬五月份 5/1~5/16
import requests
from bs4 import BeautifulSoup
import time #for sleep 禮貌
#import datetime #計算爬蟲時間，未完
start_page = 4623040 #2020-01-02 4429138 2021-01-01 4555021
end_page =   4646459 #2021-05-14 
title =[]
content = []
hashtag = []
date =[]
presenter =[]
#%%
'1萬篇 23:17 '
for page in range(start_page, end_page): 
    url = 'https://news.cnyes.com/news/id/4623040'#需更新
    url = url.replace('x', str(start_page))
    res = requests.get(url)#200 正常
    soup = BeautifulSoup(res.text, 'html.parser') 
    #開爬 不乾淨，後面.text清除
    title_get = soup.select('._uo1n h1') 
    content_get = soup.select('._2E8y')
    hashtag_get = soup.select('._1E-R') #含相關個股(拆不掉)
    date_get = soup.select('._1R6L time')
    presenter_get = soup.select('._3lKe')
    for items in range(len(title_get)):
        title.append(title_get[items].text.replace('\n', '').replace(' ', ''))
        content.append(content_get[items].text.replace('\n', '').replace(' ', ''))
        hashtag.append(hashtag_get[items].text.replace('\n', '').replace(' ', ''))
        date.append(date_get[items].text.replace('\n', '').replace(' ', ''))
        presenter.append(presenter_get[items].text.replace('\n', '').replace(' ', ''))
        print('時間:' ,date)
    time.sleep(0.1) #通常設1或.5
print(title,content,hashtag,date,presenter)
#%%
import pandas as pd
df = pd.DataFrame({'title':title, 'content':content, 'hashtag':hashtag, 'date':date, 'presenter':presenter})

df.to_csv('D:/2021-01-01~2021-05-17鉅亨.csv',encoding='utf_8_sig')

登入發表討論

直播研討會

{{ item.channelVendor }} {{ item.webinarstarted }} |

直播中

1 個回答

johnsonnnn

iT邦新手 4 級 ‧ 2021-05-19 08:35:14

最佳解答

你抓取同一個網頁是因為你的網址沒更改

url = 'https://news.cnyes.com/news/id/' + str(page) #需更新

像是第二個要抓得網頁id是4623041
這篇就沒有內文
所以要去判斷沒內文的網頁就不爬

另外tag你沒抓完整

hashtag_get = soup.select('._1qS9._2Zhy ._1E-R') #含相關個股(拆不掉)
    for i in hashtag_get:
        hashtag.append(i.text.strip())

改完的就大概這樣

#鉅亨基金新聞爬蟲 
#https://news.cnyes.com/news/cat/fund
#https://news.cnyes.com/news/id/4646317 #每篇id
#假日無文，先爬五月份 5/1~5/16
import requests
from bs4 import BeautifulSoup
import time #for sleep 禮貌
#import datetime #計算爬蟲時間，未完
start_page = 4623040 #2020-01-02 4429138 2021-01-01 4555021
end_page =   4646459 #2021-05-14 
title =[]
content = []
hashtag = []
date =[]
presenter =[]
#%%'1萬篇 23:17 '
for page in range(start_page, end_page): 
    url = 'https://news.cnyes.com/news/id/' + str(page) #需更新
    url = url.replace('x', str(start_page))
    res = requests.get(url)#200 正常


    soup = BeautifulSoup(res.text, 'html.parser') 
    #開爬 不乾淨，後面.text清除
    title_get = soup.select('._uo1n h1') 
    content_get = soup.select('._2E8y')
    hashtag_get = soup.select('._1qS9._2Zhy ._1E-R') #含相關個股(拆不掉)
    for i in hashtag_get:
        hashtag.append(i.text.strip())

    date_get = soup.select('._1R6L time')
    presenter_get = soup.select('._3lKe')

    for items in range(len(title_get)):
        title.append(title_get[items].text.replace('\n', '').replace(' ', ''))
        content.append(content_get[items].text.replace('\n', '').replace(' ', ''))
        date.append(date_get[items].text.replace('\n', '').replace(' ', ''))
        presenter.append(presenter_get[items].text.replace('\n', '').replace(' ', ''))
        print('時間:' ,date)
    time.sleep(0.1) #通常設1或.5
print(title,content,hashtag,date,presenter)

import pandas as pd
df = pd.DataFrame({'title':title, 'content':content, 'hashtag':hashtag, 'date':date, 'presenter':presenter})
df.to_csv('D:/2021-01-01~2021-05-17鉅亨.csv',encoding='utf_8_sig')