python爬取豆瓣视频信息代码

2023-01-02 09:32:47

一：代码
二：结果如下(部分例子)

这里是爬取豆瓣视频信息，用pyquery库(jquery的python库)。

一：代码

from urllib.request import quote

from pyquery import PyQuery as pq

import requests

import pandas as pd

def get_text_page(movie_name):

	'''

	函数功能：获得指定电影名的源代码

	参数：电影名

	返回值：电影名结果的源代码

	'''

	url = 'https://www.douban.com/search?q=' + movie_name

	headers = {

		'Host' : 'www.douban.com',

		'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36',

	}

	r = requests.get(url,headers = headers,timeout=5)

	return r.text

def get_last_url(this_text):

	'''

	函数功能：根据指定的源代码得到最终的网页地址

	参数：搜索结果源代码

	返回值：最终的网页地址

	'''

	doc = pq(this_text)

	lis = doc('.title a').items()

	k = 0

	this_str = ''

	for i in lis:

		# print('豆瓣搜索结果为:{0}'.format(i.text()))

		# print('地址为:{0}'.format(i.attr.href))

		# print('\n')

		if k == 0:

			this_str = i.attr.href

		k += 1

	return this_str

def the_last_page(this_url):

	'''

	函数功能：获得最终电影网页的源代码

	参数：最终的地址

	返回值：最终电影网页的源代码

	'''

	headers = {

		'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36',

	}

	r = requests.get(this_url,headers = headers,timeout=20)

	return r.text

def the_last_text(this_text,movie_name):

	'''

	函数功能：获得每一项的数据

	参数：爬取页面的源代码

	返回值：返回空

	'''

	doc = pq(this_text)

	# 获取标题

	title = doc('#content h1').text()

	# 获取海报

	photo = doc('.nbgnbg img')

	photo_url = photo.attr.src

	r = requests.get(photo_url)

	with open('{m}.jpg'.format(m = movie_name),'wb') as f:

		f.write(r.content)

	# 电影信息

	message = doc('#info').text()

	# 豆瓣评分

	grade = doc('#interest_sectl').text()

	# 剧情

	things = doc('.related-info').text()

	with open('{0}.txt'.format(movie_name),'w+') as f:

		try:

			f.writelines([title,'\n','\n\n',message,'\n\n',grade,'\n\n',things])

		except:

			f.writelines([title,'\n','\n\n',message,'\n\n',grade])

	# 演员

	# 演员名

	name = []

	person_name  = doc('.info').items()

	for i in person_name:

		name.append(i.text())

	# 演员图片地址

	person_photo = doc('#celebrities')

	j = 0

	for i in person_photo .find('.avatar').items():

		m = i.attr('style')

		person_download_url = m[m.find('(') + 1:m.find(')')]

		# 下载演员地址

		r = requests.get(person_download_url)

		try:

			with open('{name}.jpg'.format(name = name[j]),'wb') as f:

				f.write(r.content)

		except:

			continue

		j += 1

def lookUrl(this_text,my_str):

	'''

	函数功能：获得观看链接

	参数：爬取页面的源代码

	返回值：返回空

	'''

	doc = pq(this_text)

	all_url = doc('.bs li a').items()

	movie_f   = []

	movie_url = []

	for i in all_url:

		movie_f.append(i.text())

		movie_url.append(i.attr.href)

	dataframe = pd.DataFrame({'观看平台':movie_f,'观看地址':movie_url})

	dataframe.to_csv("{movie_name}的观看地址.csv".format(movie_name = my_str),index=False,encoding = 'utf_8_sig',sep=',')

def main():

	name = input('')

	my_str = name

	movie_name = quote(my_str)

	page_text = get_text_page(movie_name)	# 得指定电影名的源代码

	last_url = get_last_url(page_text)		# 根据指定的源代码得到最终的网页地址

	page_text2 = the_last_page(last_url)	# 获得最终电影网页的源代码

	the_last_text(page_text2,my_str)		# 获得每一项的数据

	lookUrl(page_text2,my_str)				# 得到并处理观看链接

main()