import re
from time import sleep
import requests
from lxml import etree
import random
import csv
 
def main(page,f):
    url = f'https://movie.douban.com/top250?start={page*25}&filter='
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.35 Safari/537.36',}
    resp = requests.get(url,headers=headers)
    tree = etree.HTML(resp.text)
    # 獲取詳情頁(yè)的鏈接列表
    href_list = tree.xpath('//*[@id="content"]/div/div[1]/ol/li/div/div[1]/a/@href')
    # 獲取電影名稱(chēng)列表
    name_list = tree.xpath('//*[@id="content"]/div/div[1]/ol/li/div/div[2]/div[1]/a/span[1]/text()')
    for url,name in zip(href_list,name_list):
        f.flush()  # 刷新文件
        try:
            get_info(url,name)  # 獲取詳情頁(yè)的信息
        except:
            pass
        sleep(1 + random.random())  # 休息
    print(f'第{i+1}頁(yè)爬取完畢')
 
def get_info(url,name):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.35 Safari/537.36',
        'Host': 'movie.douban.com',
    }
    resp = requests.get(url,headers=headers)
    html = resp.text
    tree = etree.HTML(html)
    # 導(dǎo)演
    dir = tree.xpath('//*[@id="info"]/span[1]/span[2]/a/text()')[0]
    # 電影類(lèi)型
    type_ = re.findall(r'property="v:genre">(.*?)</span>',html)
    type_ = '/'.join(type_)
    # 國(guó)家
    country = re.findall(r'地區(qū):</span> (.*?)<br',html)[0]
    # 上映時(shí)間
    time = tree.xpath('//*[@id="content"]/h1/span[2]/text()')[0]
    time = time[1:5]
    # 評(píng)分
    rate = tree.xpath('//*[@id="interest_sectl"]/div[1]/div[2]/strong/text()')[0]
    # 評(píng)論人數(shù)
    people = tree.xpath('//*[@id="interest_sectl"]/div[1]/div[2]/div/div[2]/a/span/text()')[0]
    print(name,dir,type_,country,time,rate,people)  # 打印結(jié)果
    csvwriter.writerow((name,dir,type_,country,time,rate,people))  # 保存到文件中
 
if __name__ == '__main__':
    # 創(chuàng)建文件用于保存數(shù)據(jù)
    with open('03-movie-xpath.csv','a',encoding='utf-8',newline='')as f:
        csvwriter = csv.writer(f)
        # 寫(xiě)入表頭標(biāo)題
        csvwriter.writerow(('電影名稱(chēng)','導(dǎo)演','電影類(lèi)型','國(guó)家','上映年份','評(píng)分','評(píng)論人數(shù)'))
        for i in range(10):  # 爬取10頁(yè)
            main(i,f)  # 調(diào)用主函數(shù)
            sleep(3 + random.random())

import random
import urllib.request
from bs4 import BeautifulSoup
import codecs
from time import sleep
 
def main(url, headers):
    # 發(fā)送請(qǐng)求
    page = urllib.request.Request(url, headers=headers)
    page = urllib.request.urlopen(page)
    contents = page.read()
    # 用BeautifulSoup解析網(wǎng)頁(yè)
    soup = BeautifulSoup(contents, "html.parser")
    infofile.write("")
    print('爬取豆瓣電影250: \n')
 
    for tag in soup.find_all(attrs={"class": "item"}):
        # 爬取序號(hào)
        num = tag.find('em').get_text()
        print(num)
        infofile.write(num + "\r\n")
        # 電影名稱(chēng)
        name = tag.find_all(attrs={"class": "title"})
        zwname = name[0].get_text()
        print('[中文名稱(chēng)]', zwname)
        infofile.write("[中文名稱(chēng)]" + zwname + "\r\n")
        # 網(wǎng)頁(yè)鏈接
        url_movie = tag.find(attrs={"class": "hd"}).a
        urls = url_movie.attrs['href']
        print('[網(wǎng)頁(yè)鏈接]', urls)
        infofile.write("[網(wǎng)頁(yè)鏈接]" + urls + "\r\n")
        # 爬取評(píng)分和評(píng)論數(shù)
        info = tag.find(attrs={"class": "star"}).get_text()
        info = info.replace('\n', ' ')
        info = info.lstrip()
        print('[評(píng)分評(píng)論]', info)
        # 獲取評(píng)語(yǔ)
        info = tag.find(attrs={"class": "inq"})
        if (info):  # 避免沒(méi)有影評(píng)調(diào)用get_text()報(bào)錯(cuò)
            content = info.get_text()
            print('[影評(píng)]', content)
            infofile.write(u"[影評(píng)]" + content + "\r\n")
        print('')
 
 
if __name__ == '__main__':
    # 存儲(chǔ)文件
    infofile = codecs.open("03-movie-bs4.txt", 'a', 'utf-8')
    # 消息頭
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'}
    # 翻頁(yè)
    i = 0
    while i < 10:
        print('頁(yè)碼', (i + 1))
        num = i * 25  # 每次顯示25部 URL序號(hào)按25增加
        url = 'https://movie.douban.com/top250?start=' + str(num) + '&filter='
        main(url, headers)
        sleep(5 + random.random())
        infofile.write("\r\n\r\n")
        i = i + 1
    infofile.close()

import requests
import csv
from time import sleep
import random
 
def main(page,f):
    url = 'https://club.jd.com/comment/productPageComments.action'
    params = {
        'productId': 100011483893,
        'score': 0,
        'sortType': 5,
        'page': page,
        'pageSize': 10,
        'isShadowSku': 0,
        'fold': 1
    }
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.35 Safari/537.36',
        'referer': 'https://item.jd.com/'
    }
    resp = requests.get(url,params=params,headers=headers).json()
    comments = resp['comments']
    for comment in comments:
        content = comment['content']
        content = content.replace('\n','')
        comment_time = comment['creationTime']
        score = comment['score']
        print(score,comment_time,content)
        csvwriter.writerow((score,comment_time,content))
    print(f'第{page+1}頁(yè)爬取完畢')
 
if __name__ == '__main__':
    with open('04.csv','a',encoding='utf-8',newline='')as f:
        csvwriter = csv.writer(f)
        csvwriter.writerow(('評(píng)分','評(píng)論時(shí)間','評(píng)論內(nèi)容'))
        for page in range(15):
                main(page,f)
                sleep(5+random.random())