Image-Scraper/content-parser.py at main · ysolanky/Image-Scraper · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
import json
import pandas as pd
from newspaper import Article
import newspaper
import requests
import urllib3
import urllib
import lxml
from readable_content.parser import ContentParser
import csv

urls = pd.read_csv("test.csv")
text_dict = {}
count = 0
img_urls = ["icedrive.com", "smugmug.com", "photos.google.com", "photoblog.com", "icloud.com","dropbox.com", "4shared.com",
            "imgshack", "flickr.com", "imgur.com", "freeimages.com", "imgbox.com","cluster.com", "postimages.org",
            "freeimagehosting.net", "deviantart.com", "unsplash.com", "500px.com", "pxhere.com", "pixabay.com"]

count_1 = 0
count_2 = 0
count_3 = 0
count_4 = 0
count_5 = 0
count_6 = 0
count_7 = 0

error_file = "errors-content-parser.csv"

def image_download(url, img_urls, count):

    for j in range(len(img_urls)):
        if img_urls[j] in url:
            response = requests.get(url)

            file = open(str(count) + ".png", "wb")
            file.write(response.content)
            file.close()

            return -1


for i in urls["url"]:
    while True:
        try:
            flag = 0
            if i[0:7] != "http://":
                if i[0:8] == "https://":
                    flag = 1
                elif flag != 1:
                    prefix = "http://"
                    i = prefix + i

            count = count+1
            print(i, count)

            if image_download(i, img_urls, count) == -1:
                break

            response = requests.get(i)

            article = Article(i)
            article.download()
            article.parse()

            parser = ContentParser(i)
            content = parser.get_content()

            text_dict["Title"] = article.title
            text_dict["Title"] = text_dict["Title"].replace("\n","")
            text_dict["Title"] = text_dict["Title"].replace(r"\u","")
            text_dict["URL"] = article.url
            text_dict["Effective URL"] = [resp.url for resp in response.history]
            text_dict["Date"] = article.publish_date
            text_dict["Date"] = str(text_dict["Date"])
            text_dict["Authors"] = article.authors
            text_dict["Text"] = content
            text_dict["Text"] = text_dict["Text"].replace("\n","")
            text_dict["Text"] = text_dict["Text"].replace(r"\u","")

            file_name = str(count)
            test_json = open(file_name+".json", "w")
            json.dump(text_dict, test_json)
            test_json.close()

            with open(error_file,"a") as errors:
                writer = csv.writer(errors)
                writer.writerow([count, i, "No errors"])

            break

        except newspaper.article.ArticleException as e:
            count_1 = count_1+1
            print(e, count_1)
            with open(error_file,"a") as errors:
                writer = csv.writer(errors)
                writer.writerow([count, i, e, count_1])
            break

        except requests.exceptions.TooManyRedirects as e:
            count_2 = count_2+1
            print(e,count_2)
            with open(error_file,"a") as errors:
                writer = csv.writer(errors)
                writer.writerow([count, i, e, count_2])
            break

        except UnicodeError as e:
            count_3 = count_3 + 1
            print(e, count_3)
            with open(error_file,"a") as errors:
                writer = csv.writer(errors)
                writer.writerow([count, i, e, count_3])
            break

        except requests.exceptions.ConnectionError as e:
            count_4 = count_4 + 1
            print(e,count_4)
            with open(error_file,"a") as errors:
                writer = csv.writer(errors)
                writer.writerow([count, i, e, count_4])
            break

        except urllib3.exceptions.LocationParseError as e:
            count_5 = count_5 + 1
            print(e, count_5)
            with open(error_file,"a") as errors:
                writer = csv.writer(errors)
                writer.writerow([count, i, e, count_5])
            break

        except urllib.error.URLError as e:
            count_6 =count_6 + 1
            print(e, count_6)
            with open(error_file,"a") as errors:
                writer = csv.writer(errors)
                writer.writerow([count, i, e, count_6])
            break

        except lxml.etree.ParserError as e:
            count_7 =count_7 + 1
            print(e, count_7)
            with open(error_file,"a") as errors:
                writer = csv.writer(errors)
                writer.writerow([count, i, e, count_7])
            break