动漫迷有福利啦，这个帖子教会你爬取腾讯动漫
本帖最后由 2434849827 于 2020-3-21 09:51 编辑今天弄了一上午爬取腾讯动漫，大厂的就是难爬一点，各种加密，抓了一上午的包都没抓到我要的js文件，然后我找了半天资料，发现用selenium这个模拟浏览器直接去找到动漫图片的网址，然后用request下载会比较简单，代码量比较少，但是里面涵盖的知识点比较多，给大家提供参考
import os
import time,re
import requests
from selenium import webdriver
def getChapterUrl():
headers = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36"}
name = input('请输入要下载的动漫名称:')
url2 = f'https://ac.qq.com/Comic/searchList?search={name}'
html2 = requests.get(url = url2,headers = headers)
r11 = re.findall(r'<a href="/Comic/comicInfo/id/(\d{4,})" title',html2.text)
res = requests.get(url = f'https://ac.qq.com/Comic/comicInfo/id/{r11}', headers=headers)
r1 = re.findall(r'title="(.*?)：\d{1,5}..*"',res.text)
r2 = re.findall(r'href="(/ComicView/index/id/.*/cid/.*?)"',res.text)
r3 = re.findall(r'title=".*?：\d{1,5}.([\u4e00-\u9fa5].*?)"', res.text)
del r2[-1]
url_1 = []
#print(r3)
for i in r2:
url_1.append('https://ac.qq.com'+i)
n = 0
for i in url_1:
getChapterFile(i, r1, r3)
n += 1
def getChapterFile(url,path1,path2):
# 漫画名称目录
print(url)
path=os.path.join(path1)
if not os.path.exists(path):
os.mkdir(path)
# 章节目录
path=path+'\\'+path2
if not os.path.exists(path):
os.mkdir(path)
chrome = webdriver.Chrome()
chrome.get(url)
time.sleep(4)
imgs = chrome.find_elements_by_xpath("//div[@id='mainView']/ul[@id='comicContain']//img")
for i in range(0, len(imgs)):
js="document.getElementById('mainView').scrollTop="+str((i) * 1280)
chrome.execute_script(js)
time.sleep(3)
r = re.findall(r'https://manhua.qpic.cn',imgs.get_attribute("src"))
if r:
print(imgs.get_attribute("src"))
with open(path+'\\'+str(i)+'.png', 'wb') as f:
f.write(requests.get(imgs.get_attribute("src")).content)
chrome.close()
print('下载完成')
if __name__ == '__main__':
getChapterUrl()
页:
[1]