2024-Python爬取CST信号通路图片

Python爬取CST信号通路图片
按研究分类
CST信号通路网站为https://www.cellsignal.cn/pathways/
我们爬取前要先查看robots.txt 注意爬虫协议，避免违规爬取
输入网址https://www.cellsignal.cn/robots.txt 查看，可以爬取pathway目录，具体内容见文末

爬取结果展示：爬取73份PDF，耗时 13min15.2s （增加了休眠，防止反爬）

73份信号通路图PDF

合并后

合并后PDF

爬取单个PDF

采用ipynb方式运行
代码如下：
精简版：

import requests
import re
import time
import random
from bs4 import BeautifulSoup
from urllib.request import urlopen

# 发送 HTTP 请求获取网页内容
url = r"https://www.cellsignal.cn/pathways/by-research-area"
url_root = r"https://www.cellsignal.cn/pathways/"
response = requests.get(url)
# 解析网页内容
soup = BeautifulSoup(response.content, 'html.parser')
# 查找特定 class 的 div
target_divs = soup.find_all('div',  attrs={'class': 'accordionGroup'})
results = re.findall('<li><a href="(.*?)">(.*?)</a></li>', str(target_divs),re.S)

urls=[]
for result in results:
    # print(result[0])
    title = result[0].split('/')[-1]
    pdf_url = url_root + str(title)
    # print(pdf_url)
    urls.append(pdf_url)

for url in urls:
    # 获取PDF链接
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"}
    req = requests.get(url=url, headers=headers)
    req.encoding = 'utf-8'
    html=req.text
   
    results = re.findall('<a target="_blank" id="pathway_pdf" href="(.*?)">查看 PDF 文件</a>', html,re.S)
    print(results)
    if not results:
        continue
    link = results[0]
    name = results[0].split('/')[-1]
  
    # print(link)
    # print(name)
    # 下载
    headers ={
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36'
    }
    pdfname = name
    r = requests.get(link,headers=headers)

    # 保存在当前路径
    with open(pdfname ,mode = "wb") as f:
        f.write(r.content) #图片内容写入文件

    x = random.randint(1, 4)  # 随机一个大于等于1且小于等于5的整数
    time.sleep(x)

合并PDF

采用文件运行方式

import os
from PyPDF2 import PdfMerger

# 假设单页 PDF 文件所在的目录
pdf_directory = r'E:\Coding\python_gzlab_docu\pachong_gz_vs\cst-signaling'

# 获取目录下所有的 PDF 文件路径
pdf_files = [os.path.join(pdf_directory, filename) for filename in os.listdir(pdf_directory) if filename.endswith('.pdf')]

# 根据文件的创建时间进行排序
sorted_pdf_files = sorted(pdf_files, key=lambda x: os.stat(x).st_ctime)

# 创建 PdfMerger 对象用于合并 PDF
merger = PdfMerger()

# 逐个添加 PDF 文件到合并器中
for pdf_file in sorted_pdf_files:
    merger.append(pdf_file)

# 输出合并后的 PDF 文件
output_filename = '合并后的 PDF 文件名称.pdf'
merger.write(output_filename)
merger.close()

print(f"已成功将单页 PDF 文件按创建时间顺序合并为 {output_filename}。")

注：

爬虫协议

User-agent: *
Disallow: /account
Disallow: /order
Disallow: /product/include
Disallow: /product/protocol.jsp
Disallow: /ajax
Disallow: /checkout/include
Disallow: /include
Disallow: /product/include
Disallow: /product/productDetail.jsp
Disallow: /product-comparison
Disallow: /compare-products.jsp
Disallow: /search/include
Disallow: /punchout
Disallow: /test
Disallow: /*?country=
Disallow: /productsitemap-tp.xml
Sitemap: https://www.cellsignal.cn/sitemap.xml

User-agent: AspiegelBot
Disallow: /

User-agent: cognitiveseo
Disallow: /

User-agent: Dotbot
Disallow: /

User-agent: JamesBOT
Disallow: /

User-agent: Metauri
Disallow: /

User-agent: MauiBot
Disallow: /

User-agent: MJ12Bot
Disallow: /

User-agent: Petalbot
Disallow: /

User-agent: SplitSignalBot
Disallow: /

User-agent: spyfu
Disallow: /

User-agent: WinHTTrack
Disallow: /

爬虫全部代码

全部代码：含注释

import requests
import re
import time
import random
from bs4 import BeautifulSoup
from urllib.request import urlopen


import requests
from bs4 import BeautifulSoup

# 发送 HTTP 请求获取网页内容
url = r"https://www.cellsignal.cn/pathways/by-research-area"
url_root = r"https://www.cellsignal.cn/pathways/"
response = requests.get(url)

# 解析网页内容
soup = BeautifulSoup(response.content, 'html.parser')

# 查找特定 class 的 div
target_divs = soup.find_all('div',  attrs={'class': 'accordionGroup'})

 # results = re.findall('<img.*?src="(.*?)".*?title="(.*?)"', html,re.S)
# <li><a href="/pathways/adherens-junction-dynamics-pathway">黏附连接动力学</a></li>
# results = re.findall('<li><a href="(.*?)">', html,re.S)

results = re.findall('<li><a href="(.*?)">(.*?)</a></li>', str(target_divs),re.S)
# print(results[0][0])

urls=[]
# print(cst_url[:-17])
# print(url_root)
for result in results:
    # print(result[0])
    title = result[0].split('/')[-1]
    pdf_url = url_root + str(title)
    # print(pdf_url)
    urls.append(pdf_url)

# print(urls)

# new_text = text.replace("/", "-")
# url = r"https://www.cellsignal.cn/pathways/by-research-area"    只留 https://www.cellsignal.cn/pathways/
#<li><a href="/pathways/by-research/adhesiocn-ecm-cytoskeleton-pathways">  取最后一个斜杆后的文本作title   21
#https://www.cellsignal.cn/pathways/adherens-junction-dynamics-pathway 最后真实地址
# with open('target_divs.txt','w') as file:
#         file.write(str(target_divs))
# 打印找到的 div 内容
# for div in target_divs:
#     print(div.text)
import sys
for url in urls:
    # <a target="_blank" id="pathway_pdf" href="https://media.cellsignal.cn/www/pdfs/science/pathways/Adherens_Junction.pdf" data-en-label="pathway" data-en-action="Adherens_Junction.pdf" data-en-category="downloads">查看 PDF 文件</a>
    # <a target="_blank" id="pathway_pdf" href="(.*?)" data-en-label="pathway" data-en-action="(.*?)" data-en-category="downloads">查看 PDF 文件</a>
    # [0] 为网址  [2]为名字

    #<a target="_blank" id="pathway_pdf" href="https://media.cellsignal.cn/www/pdfs/science/pathways/fibrosis-signaling.pdf" data-en-label="pathway" data-en-action="fibrosis-signaling.pdf" data-en-category="downloads">查看 PDF 文件</a>
    # 发送 HTTP 请求获取网页内容

    # response = requests.get(url)
    # # 解析网页内容
    # soup = BeautifulSoup(response.content, 'html.parser')
    # # 查找特定 class 的 div
    # target_divs = soup.find_all('div',  attrs={'class': 'accordionGroup'})

    # 获取PDF链接
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"}
    req = requests.get(url=url, headers=headers)
    req.encoding = 'utf-8'
    html=req.text
    # print(html)
    
    results = re.findall('<a target="_blank" id="pathway_pdf" href="(.*?)" data-en-label="pathway" data-en-action="(.*?)" data-en-category="downloads">', html,re.S)

    #<a target="_blank" id="pathway_pdf" href="https://media.cellsignal.cn/www/pdfs/science/pathways/Adherens_Junction.pdf">查看 PDF 文件</a>
    #<a target="_blank" id="pathway_pdf" href="(.*?)">查看 PDF 文件</a>
    results = re.findall('<a target="_blank" id="pathway_pdf" href="(.*?)">查看 PDF 文件</a>', html,re.S)
    print(results)
    if not results:
        continue
    link = results[0]
    name = results[0].split('/')[-1]
    # print("程序即将暂停，按回车键继续...")
    # input()
    print(link)
    print(name)
   

    # # 下载
    headers ={
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36'
    }

   
    pdfname = name
    # print(pdfname)
    
    r = requests.get(link,headers=headers)

    # # 保存在当前路径
    with open(pdfname ,mode = "wb") as f:
        f.write(r.content) #图片内容写入文件

    x = random.randint(1, 4)  # 随机一个大于等于1且小于等于5的整数
    time.sleep(x)

运行日志

[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/Adherens_Junction.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Adherens_Junction.pdf
Adherens_Junction.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Contribution_of_Extracellular_Matrix_to_EMT.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Contribution_of_Extracellular_Matrix_to_EMT.pdf
Contribution_of_Extracellular_Matrix_to_EMT.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Contribution_of_Soluble_Factors_to_EMT.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Contribution_of_Soluble_Factors_to_EMT.pdf
Contribution_of_Soluble_Factors_to_EMT.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Tumor_Angiogenesis.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Tumor_Angiogenesis.pdf
Tumor_Angiogenesis.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/fibrosis-signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/fibrosis-signaling.pdf
fibrosis-signaling.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Regulation_Actin.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Regulation_Actin.pdf
Regulation_Actin.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Regulation_Microtubule.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Regulation_Microtubule.pdf
Regulation_Microtubule.pdf
[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/DNA-Damage-Response.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/DNA-Damage-Response.pdf
DNA-Damage-Response.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Cell_Cycle_G2M_DNA.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Cell_Cycle_G2M_DNA.pdf
Cell_Cycle_G2M_DNA.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Cell_Cycle_G1S.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Cell_Cycle_G1S.pdf
Cell_Cycle_G1S.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/senescence-signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/senescence-signaling.pdf
senescence-signaling.pdf
[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/Apoptosis_Overview.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Apoptosis_Overview.pdf
Apoptosis_Overview.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Death_Receptor.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Death_Receptor.pdf
Death_Receptor.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Apoptosis_Mitochondrial.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Apoptosis_Mitochondrial.pdf
Apoptosis_Mitochondrial.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Apoptosis_Inhibition.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Apoptosis_Inhibition.pdf
Apoptosis_Inhibition.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/necrotic-cell-death.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/necrotic-cell-death.pdf
necrotic-cell-death.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Autophagy.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Autophagy.pdf
Autophagy.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/senescence-signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/senescence-signaling.pdf
senescence-signaling.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Autophagy.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Autophagy.pdf
Autophagy.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Insulin_Receptor.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Insulin_Receptor.pdf
Insulin_Receptor.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Warburg_Effect.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Warburg_Effect.pdf
Warburg_Effect.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Hypoxia.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Hypoxia.pdf
Hypoxia.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/glutamine-metabolism.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/glutamine-metabolism.pdf
glutamine-metabolism.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/mTor.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/mTor.pdf
mTor.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/AMPK.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/AMPK.pdf
AMPK.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/senescence-signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/senescence-signaling.pdf
senescence-signaling.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/fibrosis-signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/fibrosis-signaling.pdf
fibrosis-signaling.pdf
[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/Wnt_beta_Catenin.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Wnt_beta_Catenin.pdf
Wnt_beta_Catenin.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/TGF_beta.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/TGF_beta.pdf
TGF_beta.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Hedgehog.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Hedgehog.pdf
Hedgehog.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Notch.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Notch.pdf
Notch.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Hippo_Signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Hippo_Signaling.pdf
Hippo_Signaling.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Angiogenesis.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Angiogenesis.pdf
Angiogenesis.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/esc_pluripotency.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/esc_pluripotency.pdf
esc_pluripotency.pdf
[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/DNA_Methylation.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/DNA_Methylation.pdf
DNA_Methylation.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Histone_Methylation.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Histone_Methylation.pdf
Histone_Methylation.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Protein_Acetylation.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Protein_Acetylation.pdf
Protein_Acetylation.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Crosstalk_PostTrans.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Crosstalk_PostTrans.pdf
Crosstalk_PostTrans.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Epigenetic-Histone-H2A-H2B-H4.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Epigenetic-Histone-H2A-H2B-H4.pdf
Epigenetic-Histone-H2A-H2B-H4.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Epigenetic-Histone-H3.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Epigenetic-Histone-H3.pdf
Epigenetic-Histone-H3.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/atp-dependent-chromatin-remodeling-complexes.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/atp-dependent-chromatin-remodeling-complexes.pdf
atp-dependent-chromatin-remodeling-complexes.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Nuclear_Receptor.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Nuclear_Receptor.pdf
Nuclear_Receptor.pdf
[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/Protein_Kinase.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Protein_Kinase.pdf
Protein_Kinase.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Phospholipase.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Phospholipase.pdf
Phospholipase.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/gpcr-overview.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/gpcr-overview.pdf
gpcr-overview.pdf
[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/Toll_Like.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Toll_Like.pdf
Toll_Like.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Jak_Stat_IL_6.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Jak_Stat_IL_6.pdf
Jak_Stat_IL_6.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/T_Cell_Receptor.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/T_Cell_Receptor.pdf
T_Cell_Receptor.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/NF_kappaB.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/NF_kappaB.pdf
NF_kappaB.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Cell-Intrinsic-Innate-Immunity-Signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Cell-Intrinsic-Innate-Immunity-Signaling.pdf
Cell-Intrinsic-Innate-Immunity-Signaling.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/B_Cell_Antigen.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/B_Cell_Antigen.pdf
B_Cell_Antigen.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/inflammasome.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/inflammasome.pdf
inflammasome.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Immune-Cell-Markers-Human.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Immune-Cell-Markers-Human.pdf
Immune-Cell-Markers-Human.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Immune-Cell-Markers-Mouse.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Immune-Cell-Markers-Mouse.pdf
Immune-Cell-Markers-Mouse.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Immune-Checkpoint.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Immune-Checkpoint.pdf
Immune-Checkpoint.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/fibrosis-signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/fibrosis-signaling.pdf
fibrosis-signaling.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/car-signaling-networks.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/car-signaling-networks.pdf
car-signaling-networks.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/rheumatoid-arthritis.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/rheumatoid-arthritis.pdf
rheumatoid-arthritis.pdf
[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/ErbB_HER.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/ErbB_HER.pdf
ErbB_HER.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/SAPK_JNK.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/SAPK_JNK.pdf
SAPK_JNK.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/MAPK_ERK_Growth.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/MAPK_ERK_Growth.pdf
MAPK_ERK_Growth.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/gpcr-overview.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/gpcr-overview.pdf
gpcr-overview.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/MAPK_p38.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/MAPK_p38.pdf
MAPK_p38.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/AMPK.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/AMPK.pdf
AMPK.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/mTor.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/mTor.pdf
mTor.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Akt_PKB.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Akt_PKB.pdf
Akt_PKB.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/phosphoinositide-lipid-signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/phosphoinositide-lipid-signaling.pdf
phosphoinositide-lipid-signaling.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Protein_Kinase.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Protein_Kinase.pdf
Protein_Kinase.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Insulin_Receptor.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Insulin_Receptor.pdf
Insulin_Receptor.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Translation_eIF_4.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Translation_eIF_4.pdf
Translation_eIF_4.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Jak_Stat_IL_6.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Jak_Stat_IL_6.pdf
Jak_Stat_IL_6.pdf
[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/gpcr-overview.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/gpcr-overview.pdf
gpcr-overview.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/trem2-signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/trem2-signaling.pdf
trem2-signaling.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Vesicle_Trafficking.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Vesicle_Trafficking.pdf
Vesicle_Trafficking.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Molecular_and_Cellular_Biology_of_Alzheimers_Disease.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Molecular_and_Cellular_Biology_of_Alzheimers_Disease.pdf
Molecular_and_Cellular_Biology_of_Alzheimers_Disease.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Genetics-of-AD_web-handout.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Genetics-of-AD_web-handout.pdf
Genetics-of-AD_web-handout.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Dopamine_Parkinsons.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Dopamine_Parkinsons.pdf
Dopamine_Parkinsons.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Neuronal_Markers.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Neuronal_Markers.pdf
Neuronal_Markers.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/post-synaptic-signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/post-synaptic-signaling.pdf
post-synaptic-signaling.pdf
[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/Akt_PKB.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Akt_PKB.pdf
Akt_PKB.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/phosphoinositide-lipid-signaling.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/phosphoinositide-lipid-signaling.pdf
phosphoinositide-lipid-signaling.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/MAPK_ERK_Growth.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/MAPK_ERK_Growth.pdf
MAPK_ERK_Growth.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/MAPK_p38.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/MAPK_p38.pdf
MAPK_p38.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/gpcr-overview.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/gpcr-overview.pdf
gpcr-overview.pdf
[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/m6a-rna.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/m6a-rna.pdf
m6a-rna.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/rna-lifecycle.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/rna-lifecycle.pdf
rna-lifecycle.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Translation_eIF_4.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Translation_eIF_4.pdf
Translation_eIF_4.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Translation_eIF_2.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Translation_eIF_2.pdf
Translation_eIF_2.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Stress-Granule-PWHO-11x16.5.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Stress-Granule-PWHO-11x16.5.pdf
Stress-Granule-PWHO-11x16.5.pdf
['https://media.cellsignal.cn/www/pdfs/science/pathways/Translation_Overview.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Translation_Overview.pdf
Translation_Overview.pdf
[]
[]
[]
['https://media.cellsignal.cn/www/pdfs/science/pathways/Ubiquitin_Proteasome.pdf']
https://media.cellsignal.cn/www/pdfs/science/pathways/Ubiquitin_Proteasome.pdf
Ubiquitin_Proteasome.pdf

更新，改进

2024.10.25-01:28
可以在文件名前加上index方便排序
重新运行时间5m1.2s。 91份PDF

 if not results:
        continue
    
    index = index + 1

    link = results[0]
    name = str(index) + "-" + results[0].split('/')[-1]

最后编辑于：2024.10.25 01:28:13

人面猴
序言：七十年代末，一起剥皮案震惊了整个滨河市，随后出现的几起案子，更是在滨河造成了极大的恐慌，老刑警刘岩，带你破解...
沈念sama阅读 204,684评论 6赞 478
死咒
序言：滨河连续发生了三起死亡事件，死亡现场离奇诡异，居然都是意外死亡，警方通过查阅死者的电脑和手机，发现死者居然都...
沈念sama阅读 87,143评论 2赞 381
救了他两次的神仙让他今天三更去死
文/潘晓璐我一进店门，熙熙楼的掌柜王于贵愁眉苦脸地迎上来，“玉大人，你说我怎么就摊上这事。” “怎么了？”我有些...
开封第一讲书人阅读 151,214评论 0赞 337
道士缉凶录：失踪的卖姜人
文/不坏的土叔我叫张陵，是天一观的道长。经常有香客问我，道长，这世上最难降的妖魔是什么？我笑而不...
开封第一讲书人阅读 54,788评论 1赞 277
港岛之恋（遗憾婚礼）
正文为了忘掉前任，我火速办了婚礼，结果婚礼上，老公的妹妹穿的比我还像新娘。我一直安慰自己，他们只是感情好，可当我...
茶点故事阅读 63,796评论 5赞 368
恶毒庶女顶嫁案：这布局不是一般人想出来的
文/花漫我一把揭开白布。她就那样静静地躺着，像睡着了一般。火红的嫁衣衬着肌肤如雪。梳的纹丝不乱的头发上，一...
开封第一讲书人阅读 48,665评论 1赞 281
城市分裂传说
那天，我揣着相机与录音，去河边找鬼。笑死，一个胖子当着我的面吹牛，可吹牛的内容都是我干的。我是一名探鬼主播，决...
沈念sama阅读 38,027评论 3赞 399
双鸳鸯连环套：你想象不到人心有多黑
文/苍兰香墨我猛地睁开眼，长吁一口气：“原来是场噩梦啊……” “哼！你这毒妇竟也来了？” 一声冷哼从身侧响起，我...
开封第一讲书人阅读 36,679评论 0赞 258
万荣杀人案实录
序言：老挝万荣一对情侣失踪，失踪者是张志新（化名）和其女友刘颖，没想到半个月后，有当地人在树林里发现了一具尸体，经...
沈念sama阅读 41,346评论 1赞 299
护林员之死
正文独居荒郊野岭守林人离奇死亡，尸身上长有42处带血的脓包…… 初始之章·张勋以下内容为张勋视角年9月15日...
茶点故事阅读 35,664评论 2赞 321
白月光启示录
正文我和宋清朗相恋三年，在试婚纱的时候发现自己被绿了。大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
茶点故事阅读 37,766评论 1赞 331
活死人
序言：一个原本活蹦乱跳的男人离奇死亡，死状恐怖，灵堂内的尸体忽然破棺而出，到底是诈尸还是另有隐情，我是刑警宁泽，带...
沈念sama阅读 33,412评论 4赞 321
日本核电站爆炸内幕
正文年R本政府宣布，位于F岛的核电站，受9级特大地震影响，放射性物质发生泄漏。R本人自食恶果不足惜，却给世界环境...
茶点故事阅读 39,015评论 3赞 307
男人毒药：我在死后第九天来索命
文/蒙蒙一、第九天我趴在偏房一处隐蔽的房顶上张望。院中可真热闹，春花似锦、人声如沸。这庄子的主人今日做“春日...
开封第一讲书人阅读 29,974评论 0赞 19
一桩弑父案，背后竟有这般阴谋
文/苍兰香墨我抬头看了看天上的太阳。三九已至，却和暖如春，着一层夹袄步出监牢的瞬间，已是汗流浃背。一阵脚步声响...
开封第一讲书人阅读 31,203评论 1赞 260
情欲美人皮
我被黑心中介骗来泰国打工，没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留，地道东北人。一个月前我还...
沈念sama阅读 45,073评论 2赞 350
代替公主和亲
正文我出身青楼，却偏偏与公主长得像，于是被迫代替她去往敌国和亲。传闻我的和亲对象是个残疾皇子，可洞房花烛夜当晚...
茶点故事阅读 42,501评论 2赞 343