爬去网页时出现raise etree.ParserError(lxml.etree.ParserError: Document is empty问题，想知道哪里出现了错误源代码如下

SWDYSQBL

已于 2023-11-17 08:30:06 修改

阅读量196

点赞数 1

文章标签： python 开发语言 pycharm 网络爬虫

于 2023-11-17 08:28:43 首次发布

本文链接：https://blog.csdn.net/SWDYSQBL/article/details/134454393

版权

import requests

from urllib import response

import lxml.html

import csv

from requests import Response

doubanurl = 'https://movie.douban.com/top250?start={}&filter='

def getSource(url):

    #获取目标网页
    response = requests.get(url)
    response.encoding = 'utf-8'
    return response.content

def getEveryItem(source):

    selector = lxml.html.document_fromstring(source)

    movieItemList = selector.xpath('//div[@class="info"]')

    movieList = []

    for eachMovie in movieList:

        movieDict = {}
        title = eachMovie.xpath('div[@class="hd"]/a/span[@class="title"]/text()')
        print(title)
        otherTitle = eachMovie.xpath('div[@class="hd"]/a/span[@class="other"]/text()')
        link = eachMovie.xpath('div[@class="hd"]/a/@href')[0]
        star = eachMovie.xpath('div[@class="bd"]/div[@class="star"]/span[@class="rating_num"]/text()')
        quote = eachMovie.xpath('div[@class="bd"]/p[@class="quote"]/span/text()')

        movieDict['title'] = ''.join(title+otherTitle)
        movieDict['url'] = link
        movieDict['star'] = star
        movieDict['quote'] = quote
        print(movieDict)
        movieList.append(movieDict)
    return movieList

def writeData(movieList):
    with open('./DouBanMovie.csv','w',encoding='UTF-8')as f:
        writer = csv.DictWriter(f,fieldnames=['title','star','quote','url'])
        writer.writeheader()

        for each in movieList:
            writer.writerow(each)

if __name__ == '__main__':
    movieList = []

    for i in range(10):
        pageLink = doubanurl.format(i*25)
        print(pageLink)

        source = getSource(pageLink)

        movieList +=getEveryItem(source)

    print(movieList[:10])
    writeData(movieList)