Python爬取豆瓣高分電影前250名

import requests
import pyMySQL
import time
import re
import xlwt
from lxml import etree

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.92 Safari/537.36',
          'Cookie': 'gr_user_id = c6f58a39 - ea25 - 4f58 - b448 - 545070192c4e;59a81cc7d8c04307ba183d331c373ef6_gr_session_id = e8e4b66f - 440a - 4ae7 - a76a - fe2dd2b34a26;59a81cc7d8c04307ba183d331c373ef6_gr_last_sent_sid_with_cs1 = e8e4b66f - 440a - 4ae7 - a76a - fe2dd2b34a26;59a81cc7d8c04307ba183d331c373ef6_gr_last_sent_cs1 = N % 2FA;59a81cc7d8c04307ba183d331c373ef6_gr_session_id_e8e4b66f - 440a - 4ae7 - a76a - fe2dd2b34a26 = true;grwng_uid = 9ec14ad9 - 5ac0 - 4bb1 - 81c1 - bc60d2685710;abtest_ABTest4SearchDate = b;xzuuid = 79426b52;_uab_collina = 154660443606130958890473;TY_SESSION_ID = 907f32df - c060 - 49ca - b945 - 98215cc03475;rule_math = pvzq3r06hi'}

conn = pymysql.connect(host= 'localhost',user= 'root',passwd='momiao5201314',db='doubanmovie',port=3306,charset='utf8')
cursor = conn.cursor() #創(chuàng)建光標(biāo)對象

'''
# 創(chuàng)建一個workbook設(shè)置編碼
workbook = xlwt.Workbook(encoding = 'utf-8')
# 創(chuàng)建一個worksheet
worksheet = workbook.add_sheet('My Worksheet')
#定義表頭
header = ['movie_name','director','actors,style','country','release_time','time','score']
for h in range(len(header)):
    workbook.write(0,h,header[h])
'''

def get_movie_url(url):
    html = requests.get(url,headers=headers)
    selector = etree.HTML(html.text)
    movie_urls = selector.xpath('//div[@class="hd"]/a/@href')
    for movie_url in movie_urls:
        #print(movie_url)
        get_movie_info(movie_url)

def get_movie_info(url):
    html = requests.get(url,headers=headers)
    selector = etree.HTML(html.text)
    try:
        movie_name = selector.xpath('//*[@id="content"]/h2/span[1]/text()')  #1電影名稱
        #print(movie_name)
        director = selector.xpath('//*[@id="info"]/span[1]/span[2]/a/text()') #2導(dǎo)演
        #print(director)
        actors = selector.xpath('//*[@id="info"]/span[3]/span[2]')[0]  #Xpath疑問?
        actor = actors.xpath('string(.)')  #3演員
        #print(actor)
        style = re.findall('<span property="v:genre">(.*?)</span>',html.text,re.S)[0] + re.findall('<span property="v:genre">(.*?)</span>',html.text,re.S)[1]  #4類型
        #print(style)
        country = re.findall('<span class="pl">制片國家/地區(qū):</span>(.*?)<br/>',html.text,re.S) #5制片地區(qū)
        #print(country)
        release_time = re.findall('上映日期:</span>.*?>(.*?)</span>',html.text,re.S) #6上映時間
        #print(release_time)
        time = re.findall('<span class="pl">片長:</span>.*?>(.*?)</span>',html.text,re.S) #7片長
        #print(time)
        score = selector.xpath('//*[@id="interest_sectl"]/div[1]/div[2]/strong/text()') #8評分
        #print(score)
        print(str(movie_name))
        #sql = 'insert into doubanmovie(name,director,actor,style,country,release_time,time,score,) values("{}","{}","{}","{}","{}","{}","{}","{}")'.format(movie_name,director,actor,style,country,release_time,time,score) #多一個逗號
        cursor.execute("insert into doubanmovie(name,director,actor,style,country,release_time,time,score) values(%s,%s,%s,%s,%s,%s,%s,%s)",(str(movie_name),str(director),str(actor),str(style),str(country),str(release_time),str(time),str(score)))
    except IndexError:
        pass

if __name__ == '__main__':
    urls = ['https://movie.douban.com/top250?start={}&filter='.format(num)for num in range(0,250,25)]
    for url in urls:
        get_movie_url(url)
        time.sleep(2)
    conn.commit()

Python爬取豆瓣高分電影前250名

十余年的桂林網(wǎng)站建設(shè)經(jīng)驗，針對設(shè)計、前端、開發(fā)、售后、文案、推廣等六對一服務(wù)，響應(yīng)快，48小時及時工作處理。成都全網(wǎng)營銷推廣的優(yōu)勢是能夠根據(jù)用戶設(shè)備顯示端的尺寸不同，自動調(diào)整桂林建站的顯示方式，使網(wǎng)站能夠適用不同顯示終端，在瀏覽器中調(diào)整網(wǎng)站的寬度，無論在任何一種瀏覽器上瀏覽網(wǎng)站，都能展現(xiàn)優(yōu)雅布局與設(shè)計，從而大程度地提升瀏覽體驗。成都創(chuàng)新互聯(lián)公司從事“桂林網(wǎng)站設(shè)計”,“桂林網(wǎng)站推廣”以來，每個客戶項目都認真落實執(zhí)行。

當(dāng)前名稱：Python爬取豆瓣高分電影前250名
文章URL：http://muchs.cn/article38/ihippp.html

成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián)，為您提供定制開發(fā)、面包屑導(dǎo)航、微信小程序、虛擬主機、服務(wù)器托管、網(wǎng)站導(dǎo)航

廣告

聲明：本網(wǎng)站發(fā)布的內(nèi)容（圖片、視頻和文字）以用戶投稿、用戶轉(zhuǎn)載內(nèi)容為主，如果涉及侵權(quán)請盡快告知，我們將會在第一時間刪除。文章觀點不代表本網(wǎng)站立場，如需處理請聯(lián)系客服。電話：028-86922220；郵箱：631063699@qq.com。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載，或轉(zhuǎn)載時需注明來源： 創(chuàng)新互聯(lián)

網(wǎng)站建設(shè)網(wǎng)站維護公司