Fix page number retrieval (#25)

* Added new page number retrieval logic

* Excluded utils and bumped version

* Fixed name variable xpath

pcpartpicker/__init__.py

@@ -2,6 +2,6 @@
 from .parts import *
 
 __name__ = ["pcpartpicker"]
-__version__ = '1.2.2'
+__version__ = '1.2.3'
 __author__ = 'Jonathan Vusich'
 __email__ = 'jonathanvusich@gmail.com'

pcpartpicker/parser.py

@@ -109,7 +109,7 @@ def html_to_tokens(parse_args: Tuple[str, List[str]]) -> Tuple[str, List[List[st
     part, raw_html = parse_args
     html = [lxml.html.fromstring(html) for html in raw_html]
     tags = [page.xpath(
-        'tr/td/a/p | tr/td[contains(@class, "td__spec")] | tr/td[@class="td__price"]')
+        'tr/td/a/div[@class="td__nameWrapper"]/p | tr/td[contains(@class, "td__spec")] | tr/td[@class="td__price"]')
         for page in html]
     return part, [parse_elements(elements) for elements in tags]
 

pcpartpicker/scraper.py

@@ -1,6 +1,7 @@
 import asyncio
 from typing import List, Tuple, Iterable, Dict
 import logging
+import lxml.html
 
 import aiohttp
 
@@ -63,10 +64,12 @@ async def _retrieve_page_numbers(self, session: aiohttp.ClientSession, part: str
         """
 
         data: dict = await self._retrieve_page_data(session, part)
-        num = data["result"]["paging_data"]["page_blocks"][-1]["page"]
-        return [x for x in range(1, num + 1)]
+        num_data = data["result"]["paging_row"]
+        html_tags = lxml.html.fromstring(num_data)
+        tags = html_tags.xpath('section/ul/li')
+        return [x for x in range(1, len(tags) + 1)]
 
-    async def _retrieve_page_data(self, session: aiohttp.ClientSession, part: str, page_num: int = 1) -> str:
+    async def _retrieve_page_data(self, session: aiohttp.ClientSession, part: str, page_num: int = 1) -> dict:
         """
         Hidden method that retrieves page data for a given part type and page number.
 

setup.py

@@ -8,7 +8,7 @@ def read(file_name: str):
 
 setup(
     name="pcpartpicker",
-    version="1.2.2",
+    version="1.2.3",
     author="Jonathan Vusich",
     author_email="jonathanvusich@gmail.com",
     description="A fast, simple API for PCPartPicker.com.",
@@ -17,7 +17,7 @@ def read(file_name: str):
     license="GPL",
     keywords="pcpartpicker api webscraper",
     url="https://github.com/JonathanVusich/pcpartpicker",
-    packages=find_packages(exclude=["*.tests", "*.tests.*", "tests.*", "tests"]),
+    packages=find_packages(exclude=["*.tests", "*.tests.*", "tests.*", "tests", "utils"]),
     install_requires=read("requirements.txt"),
     classifiers=[
         "Development Status :: 5 - Production/Stable",