梨视频,电影天堂,22图床的爬虫

python/spider/Movie/22tc.py

@@ -0,0 +1,48 @@
+import re  # 正则表达式
+import requests  # 获取网页
+from bs4 import BeautifulSoup
+
+##拿到发现图片页面信息
+
+domian = "https://tc.lsy22.com/explore"
+
+i = 1
+
+UA = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36"}
+
+param = {"page": i,
+         "seek": "2023-10-20+13%3A40%3A23.5pOu"}
+
+resp = requests.get(domian, headers=UA)
+
+page = BeautifulSoup(resp.text, "html.parser")
+
+list = page.find_all("div", class_="list-item fixed-size c8 gutter-margin-right-bottom")
+
+resp.close()
+
+href = []
+##获取子页面
+for item in list:
+    href.append(item.find("div", class_="list-item-image fixed-size").find("a").get("href"))
+j = 0
+## 下载图片
+for i in range(len(list)):
+    j += 1
+    ##获取链接
+    resp = requests.get(href[i], headers=UA)
+    page = BeautifulSoup(resp.text, "html.parser")
+    image = page.find("div", class_="content-width margin-top-10").find("div",
+                                                                        class_="header header-content margin-bottom-10").find(
+        "div", class_="header-content-right").find("a").get("href")
+    ##下载图片
+    img_resp = requests.get(image, headers=UA)
+    img_name = r"image\\"+str(j)+"."+image.split(".")[-1]
+    img_file =open(img_name, "wb")
+    img_file.write(img_resp.content)
+    ##关闭下载
+    print("成功",j,"次")
+    img_file.close()
+    img_file.close()
+    resp.close()

python/spider/Movie/dianyingtiantang.py

@@ -0,0 +1,56 @@
+import re  # 正则表达式
+import requests  # 获取网页
+import warnings
+warnings.filterwarnings("ignore")#去除443警告
+
+file = open("电影天堂.txt","a+",encoding="utf-8")
+
+
+index = 1
+
+domain = "https://www.dyttcn.com"
+
+
+UA = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36"}
+
+rules1 = re.compile(r'<a href="(?P<url>.*?.html)" class="ulink" title="\d+年.*?片《.*?》.*?">.*?</a>')
+
+
+data1 = []
+
+for index in range(1, 16):
+    class_typical = f"/jingdiandapian/list_18_{index}.html"
+    resp1 = requests.get(domain + class_typical, headers=UA, verify=False)
+    resp1.close()
+    resp1.encoding = "gb2312"
+    data1.append(rules1.findall(resp1.text))
+
+
+
+
+rules2 = re.compile(r'.*?◎片　　名　(?P<name>.*?)</p>'
+                    r'.*?◎年　　代　(?P<year>\d+)</p>'
+                    r'.*?◎类　　别　(?P<class>.*?)</p>'
+                    r'.*?<a href="(?P<url>magnet:\?xt=urn:btih:.*?")>',re.S)
+
+
+
+for i in data1:
+    for j in i:
+        if type(j) == str:
+            resp2 = requests.get(domain + j, headers=UA, verify=False)
+        elif type(j) == list:
+            resp2 = requests.get(domain + j[0], headers=UA, verify=False)
+        print(j)
+        resp2.close()
+        resp2.encoding = "gb2312"
+        data2 = rules2.findall(resp2.text)
+        if len(data2) > 0:
+            print(str(data2))
+            file.write(str(data2))
+            file.write('\n')
+
+
+
+file.close()

python/spider/Movie/lishiping.py

@@ -0,0 +1,32 @@
+import re
+import requests
+
+url = "https://www.pearvideo.com/video_1792985"
+
+conID = url.split("_")[1]
+videourl = f"https://www.pearvideo.com/videoStatus.jsp?contId={conID}"
+
+header = {"Referer": url,
+          "User-Agent":
+              "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36"
+          }
+
+resp = requests.get(videourl, headers=header)
+
+dic = resp.json()
+
+srcUrl = dic["videoInfo"]["videos"]["srcUrl"]
+
+systemTime = dic["systemTime"]
+
+downloadurl = srcUrl.replace(systemTime,f"cont-{conID}")
+
+
+url =requests.get(downloadurl, headers=header)
+
+file = open("lsp.mp4","wb+")
+
+file.write(url.content)
+
+file.close()
+