[已解决]基础爬虫——爬许嵩

会计也学

有没有大哥教一下如何爬百度上的许嵩图片
import urllib.request
import re
from bs4 import BeautifulSoup
def main():
    url="https://cn.bing.com/images/search?q=%E8%AE%B8%E5%B5%A9&form=HDRSC2&first=1&tsc=ImageBasicHover"
    datalist =getData(url)
find_picture=re.compile(r'href="/image/search?(.*?)""alt="许嵩 的图像结果"/>"')
def askurl(url):
    head = {"User-Agent":" Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.55 Safari/537.36 Edg/96.0.1054.43"}
    request = urllib.request.Request(url,headers=head)
    html=""
    try:
        response = urllib.request.urlopen(request)
        html=response.read().decode("utf-8")
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)
    return html
def getData(url):
    html=askurl(url)
    soup = BeautifulSoup(html, "html.parser")
    html=str(html)
    picture= re.findall(find_picture,html)
    print(picture)
if __name__=="__main__":
    main()
我这好像很多问题，尤其是正则表达式那里，感觉写不出来合适的。系统给的结果是可以执行，但并没有执行print(picture)这一步

最佳答案

月排行榜 / 总排行榜

大马强

2022-1-10 09:14:44

正则没写对呀，当然没结果

1. import urllib.request
   
2. import re
   
3. from bs4 import BeautifulSoup
   
4. 
   
5. 
   
6. def main():
   
7.     url = "https://cn.bing.com/images/search?q=%E8%AE%B8%E5%B5%A9&form=HDRSC2&first=1&tsc=ImageBasicHover"
   
8.     datalist = getData(url)
   
9. 
   
10. # 源码图片有两种格式
    
11. # <img class="mimg" style="background-color:#925839;color:#925839" height="182" width="182" src="https://tse4-mm.cn.bing.net/th/id/OIP-C.yTXj-rc8THlpAagM9o58TAHaHa?w=182&amp;h=182&amp;c=7&amp;r=0&amp;o=5&amp;dpr=1.25&amp;pid=1.7" alt="许嵩 的图像结果"/>
    
12. # <img class="mimg vimgld" style="background-color:#3c1d19;color:#3c1d19" height="188" width="134" data-src="https://tse1-mm.cn.bing.net/th/id/OIP-C.dKR_c0_6PDuIM_ewjq7vzQHaKY?w=134&amp;h=188&amp;c=7&amp;r=0&amp;o=5&amp;dpr=1.25&amp;pid=1.7" alt="许嵩 的图像结果"/>
    
13. 
    
14. 
    
15. find_picture = re.compile(
    
16.     r'<img class="mimg.*?".*?src=(".*?") alt="许嵩 的图像结果"')
    
17. 
    
18. 
    
19. def askurl(url):
    
20.     head = {
    
21.         "User-Agent": " Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.55 Safari/537.36 Edg/96.0.1054.43"}
    
22.     request = urllib.request.Request(url, headers=head)
    
23.     html = ""
    
24.     try:
    
25.         response = urllib.request.urlopen(request)
    
26.         html = response.read().decode("utf-8")
    
27.     except urllib.error.URLError as e:
    
28.         if hasattr(e, "code"):
    
29.             print(e.code)
    
30.         if hasattr(e, "reason"):
    
31.             print(e.reason)
    
32.     # print(html)
    
33.     return html
    
34. 
    
35. 
    
36. def getData(url):
    
37.     html = askurl(url)
    
38.     soup = BeautifulSoup(html, "html.parser")
    
39.     picture = re.findall(find_picture, html)
    
40.     # for i in
    
41.     print(picture, len(picture))
    
42. 
    
43. 
    
44. if __name__ == "__main__":
    
45.     main()

复制代码

跳转到最佳答案楼层