Pyton skripta

• 0Niko još nije pohvalio poruku.
  Registruj se da bi pohvalio/la poruku!

Imam payton skriptu koj ne radi sasvim ok, a ja ne mogu da joj nadjem gresku. Ona treba da generise slektovane recenzije hotela u csv fajl i ona do uradi, ali je problem sto bez obzira na broj selekcija ona obradi samo pet. Ako neko zna neka pomogne prilazem kod

1. # !/usr/bin/python
2. # -*- coding: utf-8 -*-
3. # importing libraries
4. from bs4 import BeautifulSoup
5. import urllib, csv, os, datetime, urllib.request, re, sys
6.  
7. # creating CSV file to be used
8.  
9. file = open(os.path.expanduser(r"~/Desktop/TripAdviser Reviews.csv"), "wb")
10. file.write(
11.     b"Organization" + b"," + b"Address" + b"," + b"Reviewer" + b"," + b"Review Title" + b"," + b"Review" + b"," + b"Review Count" + b"," + b"Help Count"
12.      + b"," + b"Attraction Count" + b"," + b"Restaurant Count" + b"," + b"Hotel Count" + b"," +  b"Rating Date" + b"," + b"Rating" + b"\n")
13.  
14. # List the first page of the reviews (ends with "#REVIEWS") - separate the websites with ,
15. WebSites = [
16.     "https://www.tripadvisor.com/Hotel_Review-g294472-d7181993-Reviews-Holiday_Inn_Express_Belgrade_City-Belgrade.html"
17. ]
18. Checker = "REVIEWS"
19. # looping through each site until it hits a break
20. for theurl in WebSites:
21.     thepage = urllib.request.urlopen(theurl)
22.     soup = BeautifulSoup(thepage, 'html.parser')
23.     while True:
24.         # extract the help count, restaurant review count, attraction review count and hotel review count
25.         a = b = 0
26.         helpcountarray = restaurantarray = attractionarray = hotelarray = ""
27.  
28.         for profile in soup.findAll(attrs={"class": "memberBadgingNoText"}):
29.             textFromHt = profile.findAll(text=True)
30.             image = '\n'.join(textFromHt)
31.             image = image.replace("\n", "|||||").strip()
32.             # print "".join(profile.findAll(text=True))
33.  
34.             if image.find("helpful") > 0:
35.                 counter = image.split("helpful", 1)[0].split("|", 1)[1][-4:].replace("|", "").strip()
36.                 if len(helpcountarray) == 0:
37.                     helpcountarray = [counter]
38.                 else:
39.                     helpcountarray.append(counter)
40.             elif image.find("helpful") < 0:
41.                 if len(helpcountarray) == 0:
42.                     helpcountarray = ["0"]
43.                 else:
44.                     helpcountarray.append("0")
45.  
46.             if image.find("attraction") > 0:
47.                 counter = image.split("attraction", 1)[0].split("|", 1)[1][-4:].replace("|", "").strip()
48.                 if len(attractionarray) == 0:
49.                     attractionarray = [counter]
50.                 else:
51.                     attractionarray.append(counter)
52.             elif image.find("attraction") < 0:
53.                 if len(attractionarray) == 0:
54.                     attractionarray = ["0"]
55.                 else:
56.                     attractionarray.append("0")
57.  
58.             if image.find("REVIEWS_RESTAURANTS") > 0:
59.                 counter = image.split("REVIEWS_RESTAURANTS", 1)[0].split("|", 1)[1][-4:].replace("|", "").strip()
60.                 if len(restaurantarray) == 0:
61.                     restaurantarray = [0]
62.                 else:
63.                     restaurantarray.append("0")
64.             elif image.find("REVIEWS_RESTAURANTS") < 0:
65.                 if len(restaurantarray) == 0:
66.                     restaurantarray = ["0"]
67.                 else:
68.                     restaurantarray.append("0")
69.  
70.             if image.find("REVIEWS_HOTELS") > 0:
71.                 counter = image.split("REVIEWS_HOTELS", 1)[0].split("|", 1)[1][-4:].replace("|", "").strip()
72.                 if len(hotelarray) == 0:
73.                     hotelarray = [counter]
74.                 else:
75.                     hotelarray.append(counter)
76.             elif image.find("REVIEWS_HOTELS") < 0:
77.                 if len(hotelarray) == 0:
78.                     hotelarray = ["0"]
79.                 else:
80.                     hotelarray.append("0")
81.  
82.                     # extract the rating count for each user review
83.         #altarray = ""
84.         #for rating in soup.findAll(attrs={"class": "rating reviewItemInline"}):
85.          #   alt = rating.find('img', alt=True)
86.          #   if alt[-5:] == '':
87.           #      if len(altarray) == 0:
88.           #          altarray = [alt]
89.        # else:
90.             # noinspection PyUnboundLocalVariable
91.         #    altarray.append(alt)
92.  
93.         Organization = soup.find(attrs={'class': 'heading_title'
94.                                         }).text.replace('"', ' ').replace('Review of', ' ').strip()
95.         Address = soup.findAll(attrs={'class': 'address_search'
96.                                       })[0].text.replace(',', '').replace('\n', ''
97.                                                                           ).strip()
98.  
99.         # Loop through each review on the page
100.         for x in range(0, len(hotelarray)):
101.             # noinspection PyBroadException
102.             try:
103.                 Reviewer = soup.findAll(attrs={"class": "username mo"})[x].text
104.             except:
105.                 Reviewer = "N/A"
106.                 continue
107.  
108.             Reviewer = Reviewer.replace(',', ' ').replace('”', '').replace('“', '').replace('"', '').strip()
109.             ReviewTitle = soup.findAll(attrs={"class": "quote"})[x].text.replace(',', ' ').replace('”', '').replace('“',
110.                                                                                                                     '').replace(
111.                 '"', '').replace('é', 'e').strip()
112.             Review = soup.findAll(attrs={"class": "entry"})[x].text.replace(',', ' ').replace('\n', ' ').strip()
113.             RatingDate = soup.findAll(attrs={"class": "ratingDate"})[x].text.replace('Reviewed', ' ').replace('NEW',
114.                                                                                                               ' ').replace(
115.                 ',', ' ').strip()
116.             # Rating = altarray[x][:1]
117.             HelpCount = helpcountarray[x]
118.             AttractionCount = attractionarray[x]
119.             Restaurant = restaurantarray[x]
120.             Hotel = hotelarray[x]
121.  
122.             Record = Organization + "," + Address + "," + Reviewer + "," + ReviewTitle + "," + Review + "," + "," + HelpCount + "," + AttractionCount + "," + Restaurant + "," + Hotel + ","  + RatingDate + ","
123.             if Checker == "REVIEWS":
124.                 file.write(bytes(Record, encoding="ascii", errors='ignore') + b"\n")
125.  
126.         link = soup.find_all(attrs={"class": "nav next taLnk"})
127.         print(Organization)
128.         if len(link) == 0:
129.             break
130.         else:
131.             soup = BeautifulSoup(urllib.request.urlopen('http://www.tripadvisor.com'
132.                                                         + link[0].get('href')), 'html.parser')
133.             print(link[0].get('href'))
134.             Checker = link[0].get('href')[-7:]
135.  
136. file.close()