Python爬虫完整代码拿走不谢

对于新手做Python爬虫来说是有点难处的，前期练习的时候可以直接套用模板，这样省时省力还很方便。

使用Python爬取某网站的相关数据，并保存到同目录下Excel。

直接上代码：

1. import re
2. import urllib.error
3. import urllib.request
5. import xlwt
6. from bs4 import BeautifulSoup
9. def main():
10. baseurl ="http://jshk.com.cn"
12. datelist = getDate(baseurl)
13. savepath=".\\jshk.xls"
14. saveDate(datelist,savepath)
16. # askURL("http://jshk.com.cn/")
18. findlink = re.compile(r'<a href="(.*?)">')
19. findimg = re.compile(r'<img.*src="(.*?)"',re.S)
20. findtitle = re.compile(r'<span class="title">(.*)</span')
21. findrating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span')
22. findjudge = re.compile(r'<span>(\d*)人评价</span>')
23. findinq= re.compile(r'<span class="inq">(.*)</span>')
25. def getDate(baseurl):
26. datalist =[]
27. for i in range(0,10):
28. url=baseurl+str(i*25)
29. html=askURL(url)
30. soup = BeautifulSoup(html,"html.parser")
31. for item in soup.find_all('div',class_="item"):
32. data = []
33. item = str(item)
34. link = re.findall(findlink,item)[0]
35. data.append(link)
36. img=re.findall(findimg,item)[0]
37. data.append(img)
38. title=re.findall(findtitle,item)[0]
40. rating=re.findall(findrating,item)[0]
41. data.append(rating)
42. judge=re.findall(findjudge,item)[0]
43. data.append(judge)
44. inq=re.findall(findinq,item)
46. if len(inq)!=0:
47. inq=inq[0].replace("。","")
48. data.append(inq)
49. else:
50. data.append(" ")
51. print(data)
52. datalist.append(data)
53. print(datalist)
54. return datalist
56. def askURL(url):
57. head = {
58. "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36"}
59. request=urllib.request.Request(url,headers=head)
60. html=""
61. try:
62. response=urllib.request.urlopen(request)
63. html=response.read().decode("utf-8")
64. # print(html)
65. except urllib.error.URLError as e:
66. if hasattr(e,"code"):
67. print(e.code)
68. if hasattr(e,"reason"):
69. print(e.reason)
71. return html
73. def saveDate(datalist,savepath):
74. workbook = xlwt.Workbook(encoding='utf-8')
75. worksheet = workbook.add_sheet('电影',cell_overwrite_ok=True)
76. col =("电影详情","图片","影片","评分","评价数","概况")
77. for i in range(0,5):
78. worksheet.write(0,i,col[i])
79. for i in range(0,250):
80. print("第%d条" %(i+1))
81. data=datalist[i]
82. for j in range(0,5):
83. worksheet.write(i+1,j,data[j])
85. workbook.save(savepath)
89. if __name__ == '__main__':
90. main()
91. print("爬取完毕")

复制代码

直接复制粘贴就行。

若要更改爬取网站，则需要更改URL以及相应的html格式（代码中的“item”）。