Python爬虫之抓取猫眼电影TOP100

标签: Python爬虫  Python  Python爬虫之抓取猫眼电影TOP100  正则表达式  爬虫

运行平台:windows

Python版本:Python 3.7.0

IDE:Sublime Text

浏览器:Chrome浏览器

思路:

            1.查看网页源代码

            2.抓取单页内容

            3.正则表达式提取信息

            4.猫眼TOP100所有信息写入文件

            5.多线程抓取


1.查看网页原代码

按F12查看网页源代码发现每一个电影的信息都在“<dd></dd>”标签之中。


点开之后,信息如下:



二.抓取单页内容

   在 浏览器中打开猫眼电影网站,点击“榜单”,再点击“TOP100榜”如下图:


接下来通过以下代码获取网页源代码:

#-*-coding:utf-8-*-
import requests
from requests.exceptions import RequestException

#猫眼电影网站有反爬虫措施,设置headers后可以爬取
headers = {
	'Content-Type': 'text/plain; charset=UTF-8',
	'Origin':'https://maoyan.com',
	'Referer':'https://maoyan.com/board/4',
	'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'
	}

#爬取网页源代码
def get_one_page(url,headers):
	try:
		response =requests.get(url,headers =headers)
		if response.status_code == 200:
			return response.text
		return None
	except RequestsException:
		return None

def main():
	url = "https://maoyan.com/board/4"
	html = get_one_page(url,headers)
	print(html)

if __name__ == '__main__':
	main()

执行结果如下:



3.正则表达式提取信息

上图标示信息即为要提取的信息,代码实现如下:

#-*-coding:utf-8-*-
import requests
import re
from requests.exceptions import RequestException

#猫眼电影网站有反爬虫措施,设置headers后可以爬取
headers = {
	'Content-Type': 'text/plain; charset=UTF-8',
	'Origin':'https://maoyan.com',
	'Referer':'https://maoyan.com/board/4',
	'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'
	}

#爬取网页源代码
def get_one_page(url,headers):
	try:
		response =requests.get(url,headers =headers)
		if response.status_code == 200:
			return response.text
		return None
	except RequestsException:
		return None

#正则表达式提取信息
def parse_one_page(html):
	pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
		+'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)
	items = re.findall(pattern,html)
	for item in items:
		yield{
		'index':item[0],
		'image':item[1],
		'title':item[2],
		'actor':item[3].strip()[3:],
		'time':item[4].strip()[5:],
		'score':item[5]+item[6]
		}

def main():
	url = "https://maoyan.com/board/4"
	html = get_one_page(url,headers)
	for item in parse_one_page(html):
		print(item)

if __name__ == '__main__':
	main()

执行结果如下:



4.猫眼TOP100所有信息写入文件

上边代码实现单页的信息抓取,要想爬取100个电影的信息,先观察每一页url的变化,点开每一页我们会发现url进行变化,原url后面多了‘?offset=0’,且offset的值变化从0,10,20,变化如下:




代码实现如下:

#-*-coding:utf-8-*-
import requests
import re
import json
import os
from requests.exceptions import RequestException

#猫眼电影网站有反爬虫措施,设置headers后可以爬取
headers = {
	'Content-Type': 'text/plain; charset=UTF-8',
	'Origin':'https://maoyan.com',
	'Referer':'https://maoyan.com/board/4',
	'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'
	}

#爬取网页源代码
def get_one_page(url,headers):
	try:
		response =requests.get(url,headers =headers)
		if response.status_code == 200:
			return response.text
		return None
	except RequestsException:
		return None

#正则表达式提取信息
def parse_one_page(html):
	pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
		+'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)
	items = re.findall(pattern,html)
	for item in items:
		yield{
		'index':item[0],
		'image':item[1],
		'title':item[2],
		'actor':item[3].strip()[3:],
		'time':item[4].strip()[5:],
		'score':item[5]+item[6]
		}
#猫眼TOP100所有信息写入文件
def write_to_file(content):
	#encoding ='utf-8',ensure_ascii =False,使写入文件的代码显示为中文
	with open('result.txt','a',encoding ='utf-8') as f:
		f.write(json.dumps(content,ensure_ascii =False)+'\n')
		f.close()
#下载电影封面
def save_image_file(url,path):

	jd = requests.get(url)
	if jd.status_code == 200:
		with open(path,'wb') as f:
			f.write(jd.content)
			f.close()

def main(offset):
	url = "https://maoyan.com/board/4?offset="+str(offset)
	html = get_one_page(url,headers)
	if not os.path.exists('covers'):
		os.mkdir('covers')	
	for item in parse_one_page(html):
		print(item)
		write_to_file(item)
		save_image_file(item['image'],'covers/'+item['title']+'.jpg')

if __name__ == '__main__':
	#对每一页信息进行爬取
	for i in range(10):
		main(i*10)


爬取结果如下:


 

5.多线程抓取

进行比较,发现多线程爬取时间明显较快:


多线程:



以下为完整代码:
#-*-coding:utf-8-*-
import requests
import re
import json
import os
from requests.exceptions import RequestException
from  multiprocessing import Pool
#猫眼电影网站有反爬虫措施,设置headers后可以爬取
headers = {
	'Content-Type': 'text/plain; charset=UTF-8',
	'Origin':'https://maoyan.com',
	'Referer':'https://maoyan.com/board/4',
	'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'
	}

#爬取网页源代码
def get_one_page(url,headers):
	try:
		response =requests.get(url,headers =headers)
		if response.status_code == 200:
			return response.text
		return None
	except RequestsException:
		return None

#正则表达式提取信息
def parse_one_page(html):
	pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
		+'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)
	items = re.findall(pattern,html)
	for item in items:
		yield{
		'index':item[0],
		'image':item[1],
		'title':item[2],
		'actor':item[3].strip()[3:],
		'time':item[4].strip()[5:],
		'score':item[5]+item[6]
		}
#猫眼TOP100所有信息写入文件
def write_to_file(content):
	#encoding ='utf-8',ensure_ascii =False,使写入文件的代码显示为中文
	with open('result.txt','a',encoding ='utf-8') as f:
		f.write(json.dumps(content,ensure_ascii =False)+'\n')
		f.close()
#下载电影封面
def save_image_file(url,path):

	jd = requests.get(url)
	if jd.status_code == 200:
		with open(path,'wb') as f:
			f.write(jd.content)
			f.close()

def main(offset):
	url = "https://maoyan.com/board/4?offset="+str(offset)
	html = get_one_page(url,headers)
	if not os.path.exists('covers'):
		os.mkdir('covers')	
	for item in parse_one_page(html):
		print(item)
		write_to_file(item)
		save_image_file(item['image'],'covers/'+item['title']+'.jpg')

if __name__ == '__main__':
	#对每一页信息进行爬取
	pool = Pool()
	pool.map(main,[i*10 for i in range(10)])
	pool.close()
	pool.join()








原文链接:加载失败,请重新获取