python 爬取影視網站下載鏈接
更新時間：2021年05月28日 10:58:51 作者：GriffinLewis2001
一個簡單的爬取影視網站下載鏈接的爬蟲，非常適合新手學習，感興趣的朋友可以參考下
項目地址：
https://github.com/GriffinLewis2001/Python_movie_links_scraper
運行效果
導入模塊
import requests,re from requests.cookies import RequestsCookieJar from fake_useragent import UserAgent import os,pickle,threading,time import concurrent.futures from goto import with_goto
爬蟲主代碼
def get_content_url_name(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
content=response.text
reg=re.compile(r'<a href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" class="thumbnail-img" title="(.*?)"')
url_name_list=reg.findall(content)
return url_name_list
def get_content(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
return response.text
def search_durl(url):
content=get_content(url)
reg=re.compile(r"{'\\x64\\x65\\x63\\x72\\x69\\x70\\x74\\x50\\x61\\x72\\x61\\x6d':'(.*?)'}")
index=reg.findall(content)[0]
download_url=url[:-5]+r'/downloadList?decriptParam='+index
content=get_content(download_url)
reg1=re.compile(r'title=".*?" href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" ')
download_list=reg1.findall(content)
return download_list
def get_page(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
content=response.text
reg=re.compile(r'<a target="_blank" class="title" href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" title="(.*?)">(.*?)<\/a>')
url_name_list=reg.findall(content)
return url_name_list
@with_goto
def main():
print("=========================================================")
name=input("請輸入劇名(輸入quit退出):")
if name == "quit":
exit()
url="http://www.yikedy.co/search?query="+name
dlist=get_page(url)
print("\n")
if(dlist):
num=0
count=0
for i in dlist:
if (name in i[1]) :
print(f"{num} {i[1]}")
num+=1
elif num==0 and count==len(dlist)-1:
goto .end
count+=1
dest=int(input("\n\n請輸入劇的編號(輸100跳過此次搜尋):"))
if dest == 100:
goto .end
x=0
print("\n以下為下載鏈接:\n")
for i in dlist:
if (name in i[1]):
if(x==dest):
for durl in search_durl(i[0]):
print(f"{durl}\n")
print("\n")
break
x+=1
else:
label .end
print("沒找到或不想看\n")
完整代碼
import requests,re
from requests.cookies import RequestsCookieJar
from fake_useragent import UserAgent
import os,pickle,threading,time
import concurrent.futures
from goto import with_goto
def get_content_url_name(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
content=response.text
reg=re.compile(r'<a href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" class="thumbnail-img" title="(.*?)"')
url_name_list=reg.findall(content)
return url_name_list
def get_content(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
return response.text
def search_durl(url):
content=get_content(url)
reg=re.compile(r"{'\\x64\\x65\\x63\\x72\\x69\\x70\\x74\\x50\\x61\\x72\\x61\\x6d':'(.*?)'}")
index=reg.findall(content)[0]
download_url=url[:-5]+r'/downloadList?decriptParam='+index
content=get_content(download_url)
reg1=re.compile(r'title=".*?" href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" ')
download_list=reg1.findall(content)
return download_list
def get_page(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
content=response.text
reg=re.compile(r'<a target="_blank" class="title" href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" title="(.*?)">(.*?)<\/a>')
url_name_list=reg.findall(content)
return url_name_list
@with_goto
def main():
print("=========================================================")
name=input("請輸入劇名(輸入quit退出):")
if name == "quit":
exit()
url="http://www.yikedy.co/search?query="+name
dlist=get_page(url)
print("\n")
if(dlist):
num=0
count=0
for i in dlist:
if (name in i[1]) :
print(f"{num} {i[1]}")
num+=1
elif num==0 and count==len(dlist)-1:
goto .end
count+=1
dest=int(input("\n\n請輸入劇的編號(輸100跳過此次搜尋):"))
if dest == 100:
goto .end
x=0
print("\n以下為下載鏈接:\n")
for i in dlist:
if (name in i[1]):
if(x==dest):
for durl in search_durl(i[0]):
print(f"{durl}\n")
print("\n")
break
x+=1
else:
label .end
print("沒找到或不想看\n")
print("本軟件由CLY.所有\(zhòng)n\n")
while(True):
main()
以上就是python 爬取影視網站下載鏈接的詳細內容，更多關于python 爬取下載鏈接的資料請關注腳本之家其它相關文章！
相關文章
簡單說,閉包就是根據不同的配置信息得到不同的結果。再來看看專業(yè)的解釋:閉包（Closure）是詞法閉包（Lexical Closure）的簡稱，是引用了自由變量的函數。這個被引用的自由變量將和這個函數一同存在，即使已經離開了創(chuàng)造它的環(huán)境也不例外。2015-07-07
簡單利用conda安裝tensorflow-gpu=2.2.0的過程及問題解決
這篇文章主要介紹了簡單利用conda安裝tensorflow-gpu=2.2.0,本文給大家詳細分享問題記錄及錯誤問題解決方案，需要的朋友可以參考下2023-01-01
在Python中列表(List)是一種有序、可變的數據類型,被廣泛用于存儲和處理多個元素,這篇文章主要給大家介紹了關于Python中創(chuàng)建數值列表的4種方法,需要的朋友可以參考下2024-05-05
python json load json 數據后出現(xiàn)亂序的解決方案
今天小編就為大家分享一篇python json load json 數據后出現(xiàn)亂序的解決方案，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧2020-02-02
這篇文章主要介紹了Python程序運行原理圖文解析，分享了相關代碼示例，小編覺得還是挺不錯的，具有一定借鑒價值，需要的朋友可以參考下2018-02-02
本文主要介紹了python3里gbk編碼的問題解決，文中通過示例代碼介紹的非常詳細，對大家的學習或者工作具有一定的參考學習價值，需要的朋友們下面隨著小編來一起學習學習吧2022-08-08
本文給大家介紹的是使用Python抓取模板之家的CSS模板并打包成zip文件的代碼，使用的是單線程，非常簡單實用，這里分享給大家，有相同需求的小伙伴參考下吧。2015-03-03
解決Linux系統(tǒng)中python matplotlib畫圖的中文顯示問題
這篇文章主要介紹了解決Linux系統(tǒng)中python matplotlib畫圖的中文顯示問題,需要的朋友可以參考下2017-06-06
Python 結合opencv實現(xiàn)圖片截取和拼接代碼實踐
這篇文章主要介紹了Python 結合opencv實現(xiàn)圖片截取和拼接代碼實踐,本文通過實例代碼給大家介紹的非常詳細,對大家的學習或工作具有一定的參考借鑒價值,需要的朋友可以參考下2023-09-09
Python通過psd-tools解析PSD文件的實現(xiàn)
本文主要介紹了Python通過psd-tools解析PSD文件的實現(xiàn)，主要包括如何獲取PSD文件的基本信息、遍歷圖層、提取圖層詳細信息、保存和創(chuàng)建PSD文件，感興趣的可以了解一下2023-12-12