-
Notifications
You must be signed in to change notification settings - Fork 2
/
comixology.py
339 lines (322 loc) · 17 KB
/
comixology.py
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
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
from os import write
import requests
import urllib
from bs4 import BeautifulSoup
from fuzzywuzzy import fuzz
from time import strptime
import re
import comicutil
import comicdb
showFuture = False
urls = {'base': 'https://www.comixology.com',
'search':
{'searchBasic': 'https://www.comixology.com/search?search={}',
'searcCollectionsUrl': 'https://www.comixology.com/search/items?search={}&subType=COLLECTIONS',
'searchSeriesUrl': 'https://www.comixology.com/search/series?search={}',
'searchIssuesUrl': 'https://www.comixology.com/search/items?search={}&subType=SINGLE_ISSUES',
'SearchcomingSoonUrl': 'https://www.comixology.com/search/items?search={}&subType=comingsoon'}
}
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
def getIssueNumberFromName(name):
if "#" in name:
split = name.split()
for part in split:
if "#" in part:
return re.sub("[^0-9]", "", part)
return "UNKNOWN"
else:
return "UNKNOWN"
def get_name(name):
return re.sub(r" ?\([^)]+\)", "", name)
def fix_name(name):
part1 = name.partition(" (")[0]
part2 = re.split("#[0-999]",name,1)[-1]
return f"{part1}{part2}"
def getYearFromName(name):
try:
#return re.search('\d{4}',name).group()
return re.findall('\d{4}',name)[-1]
except:
return "UNKNOWN"
def get_year(string):
try:
year = string.split("(")[1].replace(")","")
if not bool(re.search(r'\d', year)):
return "UNKNOWN-UNKNOWN"
else:
return year
return
except:
return "UNKNOWN-UNKNOWN"
def get_issue_by_id(id):
return {}
def get_series_by_id(id):
searchResults = []
response = requests.get(id, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
page_count = 1
try:
page_count = re.sub("[^0-9]", "",soup.find("div", {"class": "pager-jump-container"}).contents[4])
except:
pass
for n in range(int(page_count)):
url = f"{id}?Issues_pg={n+1}"
response = requests.get(url, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
results = None
try:
results = soup.find("div", {"class": "list Issues"}).find_all("li", {"class": "content-item"})
except Exception as e:
return searchResults
for result in results:
link = result.find("a", {"class": "content-img-link"})['href']
name = result.find("h5", {"class": "content-title"}).contents[0].partition('(')[0].strip()
volume = result.find("h5", {"class": "content-title"}).contents[0].partition('(')[0].strip()
coverImageBase = result.find("img", {"class": "content-img"})['src'].split('https://images-na.ssl-images-amazon.com/images/S/cmx-images-prod/Item/')
coverImageMedium = 'https://images-na.ssl-images-amazon.com/images/S/cmx-images-prod/Item/{}'.format(urllib.parse.quote(coverImageBase[1]))
coverImageLarge = coverImageMedium.replace('SX312','SX360')
coverImageSmall = coverImageMedium.replace('SX312','SX170')
credits = []
try:
name = '{} {}'.format(name,result.find("h6", {"class": "content-subtitle"}).contents[0].strip('Issue ').partition('(')[0].strip())
except Exception as e:
pass
if 'Bundle' not in name:
response = requests.get(link, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
description = ""
try:
description = soup.find("section", {"class": "item-description"}).text.replace("\n","").replace("\r","").replace("\t","")
except:
pass
publisher = soup.find("h3", {"title": "Publisher"}).contents[0].strip()
credits_section = soup.find("div", {"class": "credits"})
for credit in credits_section:
try:
c = {}
c["person"] = credit.find("h2").text.strip()
role = credit.find("h2")['title']
if "art" in role.lower():
role = "Artists"
if "written" in role.lower():
role = "Writer"
if "cover" in role.lower():
role = "Cover Artist"
if "pencil" in role.lower():
role = "Penciler"
if "colored" in role.lower():
role = "Colorist"
c["role"] = role
if c not in credits:
credits.append(c)
except:
pass
genre_list = []
genres = ""
asgroup = soup.find_all("a")
for a in asgroup:
try:
if "comics-genre" in a["href"]:
genre_list.append(a.text.strip())
except:
pass
if len(genre_list) > 0:
genres = ", ".join(genre_list)
aboutTitle = soup.find_all("h4", {"class": "subtitle"})
aboutText = soup.find_all("div", {"class": "aboutText"})
breadcrumb = soup.find("div", {"class": "breadcrumb"})
publisherLInk = crubms = breadcrumb.find_all('a')[1]
volumeLink = breadcrumb.find_all('a')[2]['href'].partition('?')[0]
pageCount = aboutText[0].contents[0].strip().replace(" Pages","")
printDate = aboutText[1].contents[0].strip()
digitalDate = aboutText[2].contents[0].strip()
ageRating = aboutText[3].contents[0].strip()
issueObject = {}
issueObject['coverImageMedium'] = coverImageMedium
issueObject['coverImageSmall'] = coverImageSmall
issueObject['coverImage'] = coverImageLarge
issueObject['volumeName'] = volume
issueObject['issueName'] = get_name(soup.find("h1", {"itemprop": "name"}).contents[0])
issueObject['issueNumber'] = getIssueNumberFromName(soup.find("h1", {"itemprop": "name"}).contents[0])
issueObject['issueLink'] = link.partition('?')[0]
issueObject['volumeLink'] = volumeLink
issueObject['volumeYear'] = getYearFromName(breadcrumb.find_all('a')[2].find('h3').contents[0].strip())
issueObject['publisher'] = comicdb.map_publisher(publisher)
issueObject['credits'] = credits
issueObject['description'] = description
issueObject['genres'] = genres
issueObject['page_count'] = pageCount
dateArray = printDate.split()
issueObject['storeDate'] = '{}-{}-{}'.format(dateArray[2],dateArray[1],strptime(dateArray[0],'%B').tm_mon)
issueObject['volumeId'] = volumeLink.strip(urls["base"])
issueObject['issueId'] = link.partition('?')[0].strip(urls["base"])
searchResults.append(issueObject)
return searchResults
def search_series(query,volumeConfidence=0,issueConfidence=0):
comic_details = comicutil.get_comic_details(query)
searchResults = []
url = urls["search"]["searchSeriesUrl"]
response = requests.get(url.format(urllib.parse.quote(query)), headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
results = soup.find_all("li", {"class": "content-item"})
for result in results:
link = result.find("a", {"class": "content-img-link"})['href']
name = result.find("h5", {"class": "content-title"}).contents[0].partition('(')[0].strip()
volume = result.find("h5", {"class": "content-title"}).contents[0].partition('(')[0].strip()
coverImageBase = result.find("img", {"class": "content-img"})['src'].split('https://images-na.ssl-images-amazon.com/images/S/cmx-images-prod/Series/')
coverImageMedium = 'https://images-na.ssl-images-amazon.com/images/S/cmx-images-prod/Series/{}'.format(urllib.parse.quote(coverImageBase[1]))
coverImageLarge = coverImageMedium.replace('SX312','SX360')
coverImageSmall = coverImageMedium.replace('SX312','SX170')
if 'Bundle' not in name:
ratio = fuzz.ratio(comicutil.stripBadChars(name),f"{comic_details.series} #{comic_details.issue}")
if ratio > issueConfidence:
response = requests.get(link, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
#description = soup.find("section", {"class": "item-description"}).contents[2]
year = get_year(soup.find("div", {"class": "title"}).find("h1", {"itemprop": "name"}).contents[0])
try:
if year.split("-")[1] == "":
year = year + "PRESENT"
except:
pass
end_year = "PRESENT"
try:
if year.split("-")[1] != "":
end_year = year.split("-")[1]
except:
pass
start_year = "UNKNOWN"
try:
start_year = year.split("-")[0]
except:
pass
publisher = soup.find("h3", {"title": "Publisher"}).contents[0].strip()
aboutTitle = soup.find_all("h4", {"class": "subtitle"})
aboutText = soup.find_all("div", {"class": "aboutText"})
breadcrumb = soup.find("div", {"class": "breadcrumb"})
publisherLInk = crubms = breadcrumb.find_all('a')[1]
volumeLink = link.partition('?')[0]
issueObject = {}
issueObject['coverImageMedium'] = coverImageMedium
issueObject['coverImageSmall'] = coverImageSmall
issueObject['coverImage'] = coverImageLarge
issueObject['volumeName'] = volume
issueObject['issueName'] = name
issueObject['name'] = name
issueObject["issue_count"] = "UNKNOWN"
issueObject['link'] = link.partition('?')[0]
issueObject['year'] = year
issueObject['start_year'] = year.split("-")[0]
issueObject['end_year'] = end_year
issueObject['issueNumber'] = getIssueNumberFromName(name)
issueObject['issueLink'] = link.partition('?')[0]
issueObject['volumeLink'] = volumeLink
issueObject['volumeYear'] = start_year
issueObject['publisher'] = comicdb.map_publisher(publisher)
issueObject['volumeId'] = volumeLink.strip(urls["base"])
issueObject['issueId'] = link.partition('?')[0].strip(urls["base"])
issueObject['confidence'] = str(ratio)
issueObject['id'] = link.partition('?')[0]
searchResults.append(issueObject)
#searchResults.sort(key=lambda x: int(x['confidence']),reverse = True)
return searchResults
def search_comics(query,volumeConfidence=0,issueConfidence=0):
comic_details = comicutil.get_comic_details(query)
urlList = [urls['search']['searchIssuesUrl'],urls['search']['searcCollectionsUrl']]
if showFuture:
urlList.append(urls['search']['SearchcomingSoonUrl'])
searchResults = []
for url in urlList:
response = requests.get(url.format(urllib.parse.quote(query)), headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
results = soup.find_all("li", {"class": "content-item"})
for result in results:
link = result.find("a", {"class": "content-img-link"})['href']
name = result.find("h5", {"class": "content-title"}).contents[0].partition('(')[0].strip()
volume = result.find("h5", {"class": "content-title"}).contents[0].partition('(')[0].strip()
coverImageBase = result.find("img", {"class": "content-img"})['src'].split('https://images-na.ssl-images-amazon.com/images/S/cmx-images-prod/Item/')
coverImageMedium = 'https://images-na.ssl-images-amazon.com/images/S/cmx-images-prod/Item/{}'.format(urllib.parse.quote(coverImageBase[1]))
coverImageLarge = coverImageMedium.replace('SX312','SX360')
coverImageSmall = coverImageMedium.replace('SX312','SX170')
try:
name = '{} {}'.format(name,result.find("h6", {"class": "content-subtitle"}).contents[0].strip('Issue ').partition('(')[0].strip())
except Exception as e:
pass
if 'Bundle' not in name:
ratio = fuzz.ratio(comicutil.stripBadChars(name),f"{comic_details.series} #{comic_details.issue}")
if ratio > issueConfidence:
response = requests.get(link, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
writers = []
try:
ws = soup.find_all("h2", {"title": "Written by"})
for writer in ws:
writers.append(writer.find("a").contents[0].strip())
except:
pass
#description = soup.find("section", {"class": "item-description"}).contents[2]
publisher = soup.find("h3", {"title": "Publisher"}).contents[0].strip()
artists = []
try:
ars = soup.find_all("h2", {"title": "Art by"})
for artist in ars:
artists.append(artist.find('a').contents[0].strip())
except:
pass
coverartists = []
try:
cas = soup.find_all("h2", {"title": "Cover by"})
for coverartist in cas:
coverartists.append(coverartist.find('a').contents[0].strip())
except:
pass
year = get_year(soup.find("div", {"id": "column2"}).find("h1", {"class": "title"}).contents[0])
try:
if year.split("-")[1] == "":
year = year + "PRESENT"
except:
pass
end_year = "PRESENT"
try:
if year.split("-")[1] != "":
end_year = year.split("-")[1]
except:
pass
start_year = "UNKNOWN"
try:
start_year = year.split("-")[0]
except:
pass
aboutTitle = soup.find_all("h4", {"class": "subtitle"})
aboutText = soup.find_all("div", {"class": "aboutText"})
breadcrumb = soup.find("div", {"class": "breadcrumb"})
publisherLInk = crubms = breadcrumb.find_all('a')[1]
volumeLink = breadcrumb.find_all('a')[2]['href'].partition('?')[0]
pageCount = aboutText[0].contents[0].strip().replace(" Pages","")
printDate = aboutText[1].contents[0].strip()
digitalDate = aboutText[2].contents[0].strip()
ageRating = aboutText[3].contents[0].strip()
issueObject = {}
issueObject['coverImageMedium'] = coverImageMedium
issueObject['coverImageSmall'] = coverImageSmall
issueObject['coverImage'] = coverImageLarge
issueObject['volumeName'] = volume
issueObject['issueName'] = name
issueObject['issueNumber'] = getIssueNumberFromName(name)
issueObject['issueLink'] = link.partition('?')[0]
issueObject['volumeLink'] = volumeLink
issueObject['volumeYear'] = start_year
issueObject['publisher'] = comicdb.map_publisher(publisher)
issueObject['writers'] = writers
issueObject['artists'] = artists
issueObject['covertartists'] = coverartists
dateArray = printDate.split()
issueObject['storeDate'] = '{}-{}-{}'.format(dateArray[2],dateArray[1],strptime(dateArray[0],'%B').tm_mon)
issueObject['volumeId'] = volumeLink.strip(urls["base"])
issueObject['issueId'] = link.partition('?')[0].strip(urls["base"])
issueObject['confidence'] = str(ratio)
searchResults.append(issueObject)
return searchResults
if __name__ == "__main__":
results = get_series_by_id(" https://www.comixology.com/Batman-The-World-2021/comics-series/159559")
print(results)