import requests
import re
from lxml import etree
import pymysql
import time
conn=pymysql.connect(host='localhost',user='test',password='123456',db='xs',port=3330,charset='utf8')
cursor=conn.cursor()
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36'}
def get_url_music(url):
html=requests.get(url,headers=headers)
selector=etree.HTML(html.text)
music_hrefs=selector.xpath('//div[@class="hd"]/a/@href')
for music_href in music_hrefs:
#print(music_href)
get_music_info(music_href)
def get_music_info(url):
html=requests.get(url,headers=headers)
selector=etree.HTML(html.text)
try:
name=re.findall('<span property="v:itemreviewed">(.*?)</span>',html.text,re.S)[0]
director=selector.xpath('//*[@id="info"]/span[1]/span[2]/a/text()')[0]
actors=selector.xpath('//*[@id="info"]/span[3]/span[2]')[0]
actor=actors.xpath('string(.)')
style=re.findall('<span property="v:genre">(.*?)</span>',html.text,re.S)[0]
country=re.findall('<span class="pl">制片國家/地區:</span>(.*?)<br/>',html.text,re.S)[0]
release_time=re.findall('上映日期:</span>.*.?>(.*?)</span>',html.text,re.S)[0]
time=re.findall('片長:</span>.*?(.*?)</span>',html.text,re.S)[0]
score=selector.xpath('//*[@id="interest_sectl"]/div[1]/div[2]/strong/text()')[0]
#print(name,director,actor,style,country,release_time,time,score)
cursor.execute("insert into doubanmovie(name,director,actor,style,country,release_time,time,score) values(%s,%s,%s,%s,%s,%s,%s,%s)",(str(name),str(director),str(actor),str(style),str(country),str(release_time),str(time),str(score)))
except ImportError:
pass
if __name__=='__main__':
urls=['https://movie.douban.com/top250?start={}'.format(str(i)) for i in range(0,100,25)]
for url in urls:
#print(url)
get_url_music(url)
time.sleep(2)
運行結果 報錯
C:\Users\cdweifeng\PycharmProjects\untitled1\venv\Scripts\python.exe C:/Users/cdweifeng/PycharmProjects/untitled1/mysqltest.py
Traceback (most recent call last):
File "C:/Users/cdweifeng/PycharmProjects/untitled1/mysqltest.py", line 59, in <module>
#print(url)
File "C:/Users/cdweifeng/PycharmProjects/untitled1/mysqltest.py", line 34, in get_url_music
#print(music_href)
File "C:/Users/cdweifeng/PycharmProjects/untitled1/mysqltest.py", line 40, in get_music_info
try:
IndexError: list index out of range
求大神賜教
uj5u.com熱心網友回復：
name=re.findall('<span property="v:itemreviewed">(.*?)</span>',html.text,re.S)
應該是這樣， name 為空 ， try except 沒有處理這個例外（ ImportError 在這里用不恰當吧？），所以 IndexError: list index out of range 就拋出了。
1、檢查你的 findall 里的關鍵字是否正確。
2、 不要直接用 name=re.findall('<span property="v:itemreviewed">(.*?)</span>',html.text,re.S)[0] 這種形式，
用 name=re.findall('<span property="v:itemreviewed">(.*?)</span>',html.text,re.S)
再判斷len(name) 。
uj5u.com熱心網友回復：
這個很尷尬，我用print的時候都是正常的，但是插入資料庫的時候就報錯…轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/21428.html