91av视频/亚洲h视频/操亚洲美女/外国一级黄色毛片 - 国产三级三级三级三级

  • 大小: 5KB
    文件類型: .py
    金幣: 1
    下載: 0 次
    發(fā)布日期: 2021-05-28
  • 語言: Python
  • 標簽: 爬蟲類??豆瓣??

資源簡介

實現(xiàn)對豆瓣電影網(wǎng)站的所有電影爬取的爬蟲實例,

資源截圖

代碼片段和文件信息

#??#?-*-?coding:utf8?-*-
#coding:utf8
#?首先用于確定編碼,加上這句
from?urllib.request?import?urlopen
from?bs4?import?BeautifulSoup
#導(dǎo)入pymysql的包
import??pymysql.cursors
import?re


‘‘‘
html?=?urlopen(“https://movie.douban.com/“)
bsObj=BeautifulSoup(html“l(fā)xml“)????#將html對象轉(zhuǎn)化為BeautifulSoup對象
liList=bsObj.findAll(“l(fā)i“{“class“:“poster“})????#找到所有l(wèi)i
for?li?in?liList:
????ul=li.parent
????print(ul)
‘‘‘

x=0
k=[]
while?x<=225:
????k.append(“https://movie.douban.com/top250?start=“+str(x)+“&filter“)
????x+=25
movie=[]
print(len(k))

for?i?in?k:
????for?j?in?range(11000):
????????for?kkk?in?range(11000):
????????????pass
????print(i)
????ht=?urlopen(i)
????bsObj?=?BeautifulSoup(ht?“l(fā)xml“)??#?將html對象轉(zhuǎn)化為BeautifulSoup對象
????liList?=?bsObj.findAll(“div“{“class“:“item“})??#?找到所有a
????for?qq?in?liList:
????????#電影鏈接
????????print(“\n“qq.div.a[‘href‘])
????????movie.append(qq.div.a[‘href‘])
print(movie)
print(len(movie))

#movie=[‘https://movie.douban.com/subject/1292052/‘?‘https://movie.douban.com/subject/1295644/‘]
#movie=[]
Info=[]
for?movieurl?in?movie:
????try:
????????#print(movieurl)
????????htt=urlopen(movieurl)
????????#print(htt.info())
????????for?j?in?range(1?1000):
????????????pass
????????bsObj1?=?BeautifulSoup(htt?“l(fā)xml“)??#?將html對象轉(zhuǎn)化為BeautifulSoup對象
????????#print(bool(bsObj1))
????????#?liListmovie?=?bsObj1.findAll(“div“?{“id“:?“content“})??#?找到所有div中,id=“content“
????????#?找到某個標簽里面的內(nèi)容
????????title?=?bsObj1.findAll(“span“{“property“:“v:itemreviewed“})[0].get_text()
????????#print(“the?title?is?no?problem!“)
????????#?找到img里面的src
????????imageurl?=?bsObj1.findAll(‘img‘)[0][‘src‘]
????????#?獲取導(dǎo)演信息
????????daoyan1?=?bsObj1.findAll(“span“?{“class“:?“pl“})[0].get_text()
????????daoyan2?=?bsObj1.findAll(“a“?{“rel“:?“v:directedBy“})[0].get_text()
????????actor?=?daoyan1?+?“:“?+?daoyan2
????????#?獲取類型信息
????????kinds?=?bsObj1.findAll(“span“?{“class“:?“pl“})[3].get_text()
????????kind2?=?bsObj1.findAll(“span“?{“property“:?“v:genre“})
????????for?lll?in?kind2:
????????????kinds?+=?“/“?+?lll.get_text()
????????#?上映日期
????????#uploaddate?=?bsObj1.findAll(“span“?{“class“:?“pl“})[6].get_text()
????????uploaddate1?=?bsObj1.findAll(“span“?{“property“:?“v:initialReleaseDate“})[0].get_text()
????????parttrn?=r“\d{4}-\d{12}-\d{12}“
????????c1?=?re.findall(parttrnuploaddate1)
????????uploaddate=c1[0]
????????#?劇情簡介
????????synopsis?=?bsObj1.findAll(“span“?{“property“:?“v:summary“})[0].get_text()
????????#?豆瓣電影排名

評論

共有 條評論