Python爬取电影信息

利用火狐浏览器模拟登录爬取源码  &＃xff01; 

爬取电影天堂的影片

进行多页爬取

1、导入模块

from bs4 import BeautifulSoup
import re
import requests
from selenium import webdriver
import time

2、构建浏览器爬取多页代码 

for i in range(1, 4):#爬去第一页到第三页的信息firefox &＃61; webdriver.Firefox()firefox.get(&＃39;http://vip.1905.com/list/t_1/p%so6.shtml&＃39; % i)time.sleep(10)html &＃61; firefox.page_sourcefirefox.quit()

3、解析页面 

soup &＃61; BeautifulSoup(html, &＃39;lxml&＃39;)for soups in soup.find_all(class_&＃61;&＃39;borderBox&＃39;):for scores in soups.find_all(class_&＃61;&＃39;fr score&＃39;):for score in scores:print("得分:", score)for titles in soups.find_all(class_&＃61;&＃39;name&＃39;):for title in titles:print("剧名:", title)for years in soups.find_all(class_&＃61;&＃39;hidden year&＃39;):for year in years:print("时间:", year)for zhu_actors in soups.find_all(class_&＃61;"hidden actor"):for zhu_actor in zhu_actors:print("主演:", zhu_actor)for pages in soups.find_all(class_&＃61;&＃39;hidden descr&＃39;):for page in pages:print("简介:", page)for urls in soups.find_all(class_&＃61;&＃39;hidden url&＃39;):for url in urls:print("网址:", url)

4、保存解析信息 

with open(&＃39;file1.txt&＃39;, &＃39;a&＃43;&＃39;, encoding&＃61;&＃39;utf-8&＃39;)as f:f.write("得分&＃xff1a;"&＃43;score&＃43;&＃39;\n&＃39;&＃43;"标题&＃xff1a;"&＃43;title&＃43;&＃39;\n&＃39;&＃43;"时间&＃xff1a;"&＃43;year&＃43;&＃39;\n&＃39; &＃43;"主演&＃xff1a;" &＃43;zhu_actor&＃43;&＃39;\n&＃39;&＃43;"简介&＃xff1a;"&＃43;page&＃43;&＃39;\n&＃39;&＃43;"网址&＃xff1a;"&＃43;url&＃43;&＃39;\n&＃39;)f.write(&＃39;&＃61;&＃39;*50&＃43;&＃39;\n&＃39;)

5、提取图片并保存 

patter &＃61; re.compile(&＃39;&＃39;)imgs &＃61; re.findall(patter, html)print(imgs)for img in imgs:url &＃61; &＃39;http:&＃39; &＃43; imgprint(img)tupian &＃61; img.split(&＃39;/&＃39;)[-1]res &＃61; requests.get(url)with open(&＃39;D:\爬虫\Video&＃39; &＃43; &＃39;\\&＃39; &＃43; tupian, &＃39;ab&＃39;)as f:f.write(res.content)

完整代码如下&＃xff1a; 

from bs4 import BeautifulSoup
import re
import requests
from selenium import webdriver
import timefor i in range(1, 4):#爬去第一页到第三页的信息firefox &＃61; webdriver.Firefox()firefox.get(&＃39;http://vip.1905.com/list/t_1/p%so6.shtml&＃39; % i)time.sleep(10)html &＃61; firefox.page_sourcefirefox.quit()soup &＃61; BeautifulSoup(html, &＃39;lxml&＃39;)for soups in soup.find_all(class_&＃61;&＃39;borderBox&＃39;):for scores in soups.find_all(class_&＃61;&＃39;fr score&＃39;):for score in scores:print("得分:", score)for titles in soups.find_all(class_&＃61;&＃39;name&＃39;):for title in titles:print("剧名:", title)for years in soups.find_all(class_&＃61;&＃39;hidden year&＃39;):for year in years:print("时间:", year)for zhu_actors in soups.find_all(class_&＃61;"hidden actor"):for zhu_actor in zhu_actors:print("主演:", zhu_actor)for pages in soups.find_all(class_&＃61;&＃39;hidden descr&＃39;):for page in pages:print("简介:", page)for urls in soups.find_all(class_&＃61;&＃39;hidden url&＃39;):for url in urls:print("网址:", url)with open(&＃39;file1.txt&＃39;, &＃39;a&＃43;&＃39;, encoding&＃61;&＃39;utf-8&＃39;)as f:f.write("得分&＃xff1a;"&＃43;score&＃43;&＃39;\n&＃39;&＃43;"标题&＃xff1a;"&＃43;title&＃43;&＃39;\n&＃39;&＃43;"时间&＃xff1a;"&＃43;year&＃43;&＃39;\n&＃39; &＃43;"主演&＃xff1a;" &＃43;zhu_actor&＃43;&＃39;\n&＃39;&＃43;"简介&＃xff1a;"&＃43;page&＃43;&＃39;\n&＃39;&＃43;"网址&＃xff1a;"&＃43;url&＃43;&＃39;\n&＃39;)f.write(&＃39;&＃61;&＃39;*50&＃43;&＃39;\n&＃39;)patter &＃61; re.compile(&＃39;&＃39;)imgs &＃61; re.findall(patter, html)print(imgs)for img in imgs:url &＃61; &＃39;http:&＃39; &＃43; imgprint(img)tupian &＃61; img.split(&＃39;/&＃39;)[-1]res &＃61; requests.get(url)with open(&＃39;D:\爬虫\Video&＃39; &＃43; &＃39;\\&＃39; &＃43; tupian, &＃39;ab&＃39;)as f:f.write(res.content)

利用火狐浏览器模拟登录爬取源码  &＃xff01;

运行代码出现下面的图示&＃xff1a;